© 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. 13746
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and investigations

    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
    744
    +0.12
    0.5%
    706
    +0.12
    0.5%
    6
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.12
    0.10
    633
    +0.12
    0.10
    706
    +0.12
    0.11
    Negative Logits
    xual
    -0.85
    idon
    -0.80
     seiz
    -0.79
     cous
    -0.79
     challeng
    -0.77
     sacrific
    -0.75
    glomer
    -0.73
    risk
    -0.71
    pora
    -0.71
    undai
    -0.68
    POSITIVE LOGITS
    ifications
    1.42
    ifiable
    1.31
    IFIC
    1.10
    IFIED
    1.06
    if
    1.05
    ices
    1.03
    itia
    1.03
    ifiers
    1.02
    ifi
    0.99
    ifier
    0.99
    Activations Density 8.403%

    No Known Activations