© 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. 45773
    Prev
    Next
    INDEX
    Explanations

    terms related to computer security threats and vulnerabilities

    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
    +0.19
    0.8%
    71
    +0.14
    0.6%
    320
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.19
    0.11
    548
    +0.14
    0.00
    640
    +0.12
    0.30
    Negative Logits
     coli
    -0.85
     Territories
    -0.68
    ":[{"
    -0.68
    ADA
    -0.68
    enhagen
    -0.67
     licens
    -0.66
    PsyNetMessage
    -0.63
    ©¶æ¥µ
    -0.63
    Published
    -0.61
     academia
    -0.60
    POSITIVE LOGITS
    itiveness
    0.96
    yip
    0.92
    gran
    0.77
    otos
    0.77
    jri
    0.74
    culosis
    0.74
    itionally
    0.72
    terness
    0.68
    ancy
    0.67
     XL
    0.67
    Activations Density 22.738%

    No Known Activations