© 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. 302
    Prev
    Next
    INDEX
    Explanations

    references to legal issues and 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
    365
    +0.15
    0.6%
    496
    +0.15
    0.5%
    343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.15
    0.03
    70
    +0.15
    0.03
    651
    +0.14
    0.02
    Negative Logits
    uality
    -1.08
    anthrop
    -0.88
     mund
    -0.87
    mph
    -0.77
    uously
    -0.76
    ttp
    -0.75
    dash
    -0.75
     vomiting
    -0.75
     Perez
    -0.74
    Redd
    -0.73
    POSITIVE LOGITS
    ership
    1.43
    ers
    1.24
    er
    1.14
    arest
    0.97
    aneers
    0.95
     Thumbnails
    0.94
    hyde
    0.93
    ukong
    0.93
    Constructed
    0.92
    places
    0.90
    Activations Density 0.179%

    No Known Activations