© 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. 45949
    Prev
    Next
    INDEX
    Explanations

    references to historical and political events related to colonialism and nationalism

    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
    +0.17
    0.9%
    130
    +0.07
    0.4%
    564
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.28
    711
    +0.07
    0.07
    251
    +0.07
    0.11
    Negative Logits
    ispers
    -0.72
    eworks
    -0.70
    ancies
    -0.66
    ravings
    -0.66
    doms
    -0.65
    ptions
    -0.64
     interviews
    -0.63
    tails
    -0.63
     stamps
    -0.62
    asions
    -0.62
    POSITIVE LOGITS
     conduit
    0.74
     spokesperson
    0.72
     contender
    0.71
     entity
    0.71
     sleeper
    0.70
     whore
    0.69
     affair
    0.68
     underdog
    0.67
     fighter
    0.66
     organism
    0.66
    Activations Density 14.413%

    No Known Activations