© 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. 7046
    Prev
    Next
    INDEX
    Explanations

    information related to legal regulations and restrictions, with a focus on ordinances and age restrictions

    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
    311
    +0.15
    0.6%
    503
    +0.15
    0.5%
    48
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.20
    651
    +0.15
    0.12
    48
    +0.14
    0.10
    Negative Logits
    в
    -0.97
    20439
    -0.90
    BOOK
    -0.88
    tips
    -0.85
    PsyNetMessage
    -0.81
    crop
    -0.80
    bill
    -0.79
    ktop
    -0.78
     palms
    -0.78
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.78
    POSITIVE LOGITS
    inance
    1.37
    ination
    1.34
    inated
    1.32
    ained
    1.25
    raction
    1.23
    inations
    1.21
    inating
    1.17
    acements
    1.17
    ined
    1.16
    ishment
    1.16
    Activations Density 4.357%

    No Known Activations