© 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. 33011
    Prev
    Next
    INDEX
    Explanations

    words related to issues and policies around drugs and the war on drugs

    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
    +0.10
    0.5%
    311
    +0.09
    0.5%
    150
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    -0.01
    150
    +0.09
    0.08
    471
    +0.09
    0.09
    Negative Logits
    SourceFile
    -0.74
    ahime
    -0.70
    RECT
    -0.67
    âĵĺ
    -0.67
    encies
    -0.66
    soDeliveryDate
    -0.63
    inventoryQuantity
    -0.63
    aird
    -0.62
    rete
    -0.61
    VP
    -0.61
    POSITIVE LOGITS
     behalf
    0.82
    etime
    0.63
     terror
    0.62
     wheels
    0.59
    erous
    0.57
     earth
    0.56
     Sundays
    0.55
     Thanksgiving
    0.55
     reform
    0.54
     Wheels
    0.54
    Activations Density 6.286%

    No Known Activations