© 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. 34791
    Prev
    Next
    INDEX
    Explanations

    words related to international trade agreements and economic impacts

    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
    281
    +0.09
    0.5%
    616
    +0.09
    0.5%
    623
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.09
    701
    +0.09
    0.07
    284
    +0.08
    0.10
    Negative Logits
    ĸļ
    -0.64
     Mehran
    -0.63
    bilt
    -0.56
    matically
    -0.52
     Patton
    -0.50
    laughs
    -0.50
    escription
    -0.49
    reon
    -0.49
    matic
    -0.49
     sidew
    -0.48
    POSITIVE LOGITS
    auld
    0.63
    rities
    0.58
    utan
    0.58
    ista
    0.57
    ectar
    0.57
     Breast
    0.56
    istas
    0.55
    é£
    0.53
    nia
    0.53
    eta
    0.53
    Activations Density 6.356%

    No Known Activations