© 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. 45985
    Prev
    Next
    INDEX
    Explanations

    locations, proper names, and words related to military and physical activities

    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
    12
    +0.10
    0.6%
    267
    +0.08
    0.4%
    331
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.10
    0.06
    664
    +0.08
    0.08
    294
    +0.08
    0.02
    Negative Logits
    ALSE
    -0.62
    »Ĵ
    -0.56
    ENDED
    -0.56
    OLOG
    -0.55
     Prohibition
    -0.55
    ACTION
    -0.54
    OLOGY
    -0.54
    200000
    -0.54
    essim
    -0.52
    ylum
    -0.51
    POSITIVE LOGITS
    dale
    0.73
    heed
    0.72
    utenant
    0.65
    warm
    0.61
    vel
    0.60
    bone
    0.59
    boat
    0.58
    leaf
    0.57
    ãĤ¨ãĥ«
    0.56
    sey
    0.56
    Activations Density 10.900%

    No Known Activations