© 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. 36380
    Prev
    Next
    INDEX
    Explanations

    text related to structural elements or changes

    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
    +0.22
    1.1%
    288
    +0.12
    0.6%
    575
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.22
    0.31
    375
    +0.12
    0.06
    362
    +0.11
    0.13
    Negative Logits
     Garland
    -0.70
    cli
    -0.67
    rising
    -0.66
    yah
    -0.65
    hawks
    -0.63
    istle
    -0.63
    travel
    -0.62
     grandson
    -0.61
    aire
    -0.61
    zig
    -0.60
    POSITIVE LOGITS
    urally
    1.07
    ural
    0.90
     structured
    0.79
     structures
    0.79
     structure
    0.77
    ured
    0.77
     Struct
    0.74
    ivist
    0.71
    itionally
    0.71
    ational
    0.70
    Activations Density 15.515%

    No Known Activations