© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    news articles and information related to legal cases and controversies, as well as criminal activities

    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
    496
    +0.15
    0.5%
    649
    +0.15
    0.5%
    453
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.15
    0.05
    231
    +0.15
    0.04
    339
    +0.14
    0.04
    Negative Logits
    stood
    -1.04
    geries
    -0.96
    apers
    -0.95
    grass
    -0.94
    ocl
    -0.94
    sole
    -0.92
     academia
    -0.91
    lets
    -0.88
    ajo
    -0.88
    ococ
    -0.88
    POSITIVE LOGITS
     VIDEOS
    1.66
     STOR
    1.34
    MORE
    1.31
     IMAGES
    1.29
     WATCHED
    1.25
    TY
    1.22
     STORY
    1.22
     ALSO
    1.22
    VERTISEMENT
    1.20
    TIME
    1.20
    Activations Density 0.644%

    No Known Activations