© 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. 4105
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and proceedings

    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
    1.2%
    425
    +0.14
    0.6%
    154
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.28
    0.15
    711
    +0.14
    0.03
    154
    +0.12
    0.15
    Negative Logits
    ©¶æ¥µ
    -0.75
    ŃĶ
    -0.64
     Conver
    -0.59
     Depth
    -0.59
    ãĥķãĤ©
    -0.58
    ~~~~~~~~
    -0.57
    password
    -0.57
    ¬¼
    -0.56
     Gutenberg
    -0.56
    @#
    -0.55
    POSITIVE LOGITS
     nor
    0.88
     versus
    0.79
    doms
    0.72
     AND
    0.71
     and
    0.71
     sexes
    0.69
     vs
    0.68
     statically
    0.64
    "]=>
    0.60
    ipolar
    0.58
    Activations Density 32.289%

    No Known Activations