© 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. 35783
    Prev
    Next
    INDEX
    Explanations

    solutions to problems or puzzles

    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
    +0.30
    1.3%
    270
    +0.11
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.30
    0.26
    578
    +0.11
    0.06
    393
    +0.10
    0.26
    Negative Logits
    interstitial
    -1.04
    cious
    -0.88
    cius
    -0.86
    eries
    -0.85
    agos
    -0.83
    awn
    -0.83
    staking
    -0.80
    Crystal
    -0.80
    oil
    -0.79
    antry
    -0.76
    POSITIVE LOGITS
     how
    1.08
     why
    0.87
     HOW
    0.86
     ways
    0.83
     WHY
    0.82
     whats
    0.80
    tle
    0.78
    llor
    0.78
     what
    0.76
    OTAL
    0.72
    Activations Density 11.946%

    No Known Activations