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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 45885
    Prev
    Next
    INDEX
    Explanations

    dates and specific events related to individuals' experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.28
    1.4%
    393
    +0.20
    1.0%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.31
    640
    +0.20
    0.28
    375
    +0.12
    0.08
    Negative Logits
    entimes
    -0.68
     antioxid
    -0.65
    OGR
    -0.60
    ¬¼
    -0.58
    ĺ
    -0.58
    ©¶æ¥µ
    -0.56
    itionally
    -0.56
    SQL
    -0.55
    Ĥª
    -0.55
    kin
    -0.54
    POSITIVE LOGITS
     respectively
    0.68
    when
    0.68
     thence
    0.66
     EDT
    0.60
     partName
    0.59
     onwards
    0.56
     PDT
    0.56
    accompanied
    0.55
     Sgt
    0.55
     whichever
    0.54
    Activations Density 12.363%

    No Known Activations