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

    Neuronpedia

    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. 14510
    Prev
    Next
    INDEX
    Explanations

    web domain names

    oai_token-act-pair · gpt-3.5-turbo
    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
    174
    +0.18
    0.6%
    543
    +0.13
    0.5%
    186
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.18
    0.05
    95
    +0.13
    0.05
    477
    +0.13
    0.04
    Negative Logits
    hetti
    -0.94
     schizophren
    -0.89
     Frie
    -0.86
    instead
    -0.83
     psychiat
    -0.83
    abet
    -0.83
    UID
    -0.81
    adobe
    -0.81
     proced
    -0.81
     Balt
    -0.81
    POSITIVE LOGITS
    #$
    0.99
     Ltd
    0.94
    lishing
    0.89
    miah
    0.89
     domain
    0.89
    psons
    0.89
    legate
    0.88
    pleting
    0.86
    thren
    0.86
    edia
    0.84
    Activations Density 0.725%

    No Known Activations