© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1169
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of restoration or reversal

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "restore" and related terms indicating a return to a previous state or condition

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    566
    +0.14
    0.6%
    240
    +0.13
    0.6%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.14
    0.05
    642
    +0.13
    0.03
    288
    +0.13
    0.07
    Negative Logits
    rics
    -0.93
    QB
    -0.85
    chens
    -0.84
    kers
    -0.82
    Cola
    -0.80
    gerald
    -0.78
    onne
    -0.75
    edin
    -0.74
    ks
    -0.73
    wer
    -0.73
    POSITIVE LOGITS
     havoc
    0.83
    itial
    0.82
     restore
    0.82
    shire
    0.81
     vig
    0.78
    imar
    0.76
     harmony
    0.76
     restoration
    0.76
     restoring
    0.74
    owship
    0.73
    Activations Density 0.791%

    No Known Activations