© 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. 33055
    Prev
    Next
    INDEX
    Explanations

    quotations commonly used in literary works or articles

    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
    +0.20
    1.0%
    314
    +0.13
    0.6%
    160
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.29
    160
    +0.13
    0.24
    739
    +0.12
    0.06
    Negative Logits
     Alger
    -0.68
     affiliate
    -0.67
     exhaustion
    -0.66
     seasoned
    -0.64
     sympathetic
    -0.63
     tabloid
    -0.63
     Stephenson
    -0.63
     Klu
    -0.63
     puberty
    -0.62
     synd
    -0.62
    POSITIVE LOGITS
    cheat
    0.98
    Big
    0.97
    Hello
    0.96
    Golden
    0.94
    almost
    0.94
    Welcome
    0.94
    Ultra
    0.94
    little
    0.92
    inventoryQuantity
    0.92
    Round
    0.91
    Activations Density 14.368%

    No Known Activations