© 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
    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. 32256
    Prev
    Next
    INDEX
    Explanations

    and emphasize specific content or information within a larger context

    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
    +0.27
    1.3%
    288
    +0.12
    0.6%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.27
    0.23
    608
    +0.12
    0.28
    393
    +0.11
    0.32
    Negative Logits
    itte
    -0.74
    cas
    -0.70
    thood
    -0.68
    cill
    -0.67
    entric
    -0.66
    hell
    -0.66
    ja
    -0.65
    onew
    -0.64
    atorial
    -0.64
    atern
    -0.62
    POSITIVE LOGITS
     reel
    0.97
    ibility
    0.83
    ibilities
    0.81
     highlights
    0.81
    iary
    0.71
     highlighting
    0.68
    Marginal
    0.68
    TextColor
    0.68
     warnings
    0.66
    OWS
    0.65
    Activations Density 13.217%

    No Known Activations