© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 31839
    Prev
    Next
    INDEX
    Explanations

    financial and economic information, including revenue, income, profit, growth rates, and other related data

    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
    436
    +0.10
    0.6%
    651
    +0.10
    0.5%
    393
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.17
    274
    +0.10
    0.11
    488
    +0.09
    0.11
    Negative Logits
    REDACTED
    -0.64
    yout
    -0.62
     advis
    -0.59
    atem
    -0.56
     psychic
    -0.56
    CLASSIFIED
    -0.55
    FUL
    -0.55
    CHAT
    -0.55
    ITNESS
    -0.54
    HOU
    -0.54
    POSITIVE LOGITS
     ago
    0.82
     Ago
    0.75
    terms
    0.73
    ibia
    0.70
    frames
    0.65
     olds
    0.65
    ago
    0.64
    gap
    0.63
     averages
    0.62
    period
    0.61
    Activations Density 6.615%

    No Known Activations