© 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. 6160
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and correctional procedures

    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
    149
    +0.04
    0.6%
    298
    +0.03
    0.5%
    566
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.04
    0.04
    590
    +0.03
    0.03
    508
    +0.03
    0.03
    Negative Logits
    fold
    -0.19
    ________________
    -0.18
    hood
    -0.18
    wired
    -0.18
    joy
    -0.18
    broad
    -0.18
    essler
    -0.17
    ãĥł
    -0.17
    founded
    -0.17
    bish
    -0.17
    POSITIVE LOGITS
     Facility
    0.28
     Institution
    0.25
     Intercept
    0.23
     Corps
    0.22
     Technologies
    0.22
     Facilities
    0.22
     Industry
    0.22
     Corporation
    0.22
     Services
    0.22
     Cooperative
    0.22
    Activations Density 0.118%

    No Known Activations