© 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. 13361
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making, advice, and troubleshooting

    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
    240
    +0.16
    0.6%
    393
    +0.15
    0.5%
    598
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.16
    0.08
    240
    +0.15
    0.06
    598
    +0.15
    0.06
    Negative Logits
    theless
    -0.95
     glances
    -0.88
    ropolitan
    -0.87
     muse
    -0.84
    mint
    -0.83
    inch
    -0.80
    ãģ£
    -0.78
    wreck
    -0.77
    女
    -0.77
     disbelief
    -0.75
    POSITIVE LOGITS
    othes
    1.49
    bered
    1.46
    othe
    1.38
    oner
    1.27
    oths
    1.26
    apy
    1.24
    ooo
    1.14
    arer
    1.13
    aps
    1.12
    oooo
    1.10
    Activations Density 1.119%

    No Known Activations