© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 4920
    Prev
    Next
    INDEX
    Explanations

    information regarding legal restrictions or prohibitions

    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
    +0.06
    1.0%
    393
    +0.03
    0.6%
    31
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.06
    0.31
    159
    +0.03
    0.10
    614
    +0.03
    0.05
    Negative Logits
    ppe
    -0.20
    hran
    -0.19
    rh
    -0.19
    gypt
    -0.18
     congr
    -0.18
    ãĤ©
    -0.17
    inton
    -0.17
    cards
    -0.17
    Js
    -0.17
    lectic
    -0.17
    POSITIVE LOGITS
     violation
    0.23
     ILCS
    0.22
     other
    0.21
     improper
    0.21
     unauthorized
    0.21
     combination
    0.20
     subsequent
    0.20
     substitute
    0.20
     unlawful
    0.20
     person
    0.19
    Activations Density 13.322%

    No Known Activations