© 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. 45954
    Prev
    Next
    INDEX
    Explanations

    references to political events and policies

    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
    393
    +0.20
    1.2%
    447
    +0.13
    0.8%
    636
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.37
    393
    +0.13
    0.33
    385
    +0.13
    0.31
    Negative Logits
    Joined
    -0.68
    allah
    -0.57
    ohan
    -0.56
    emp
    -0.55
    autions
    -0.54
    veland
    -0.54
    arten
    -0.53
    ventures
    -0.52
    hari
    -0.52
     obe
    -0.51
    POSITIVE LOGITS
     aforementioned
    0.78
     latter
    0.74
     dreaded
    0.69
     latest
    0.59
     remainder
    0.59
     largest
    0.58
     sexes
    0.57
     entire
    0.56
     nation
    0.56
     elusive
    0.55
    Activations Density 8.215%

    No Known Activations