© 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. 6688
    Prev
    Next
    INDEX
    Explanations

    instances of sentences describing events or dialogues in a narrative style

    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
    87
    +0.83
    14.6%
    266
    +0.29
    5.1%
    480
    +0.14
    2.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.83
    0.40
    480
    +0.29
    0.15
    464
    +0.14
    0.32
    Negative Logits
    ccording
    -0.18
    NetMessage
    -0.17
    actionDate
    -0.17
    pmwiki
    -0.16
    Reviewer
    -0.15
    ongyang
    -0.15
    nai
    -0.15
    enegger
    -0.14
    VIDIA
    -0.14
    xus
    -0.14
    POSITIVE LOGITS
    ©¶æ
    0.19
    aeper
    0.14
     Pound
    0.13
    rums
    0.13
     stra
    0.12
     scissors
    0.12
    boat
    0.11
     equally
    0.11
     bush
    0.11
     extensively
    0.11
    Activations Density 12.001%

    No Known Activations