© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12516
    Prev
    Next
    INDEX
    Explanations

    financial terms or information, including expenses, revenue, losses, and liabilities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    728
    +0.10
    0.6%
    298
    +0.08
    0.4%
    575
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.10
    0.01
    248
    +0.08
    0.01
    150
    +0.08
    0.01
    Negative Logits
    tz
    -0.64
    Chel
    -0.61
    Jess
    -0.53
     Woods
    -0.53
    NES
    -0.53
     Chel
    -0.53
    RGB
    -0.50
    BTC
    -0.49
    utf
    -0.49
     DJs
    -0.48
    POSITIVE LOGITS
    iture
    0.66
    itures
    0.65
     revolving
    0.58
     Gund
    0.56
    perty
    0.56
     renovations
    0.53
    urable
    0.52
    ional
    0.52
    ault
    0.52
    glomer
    0.51
    Activations Density 0.015%

    No Known Activations