© 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 EvalsExportsinterp-engineNEWAPI 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. 2747
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement incidents and legal proceedings

    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
    44
    +0.15
    0.6%
    177
    +0.13
    0.5%
    525
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.24
    146
    +0.13
    0.14
    575
    +0.12
    0.16
    Negative Logits
    mble
    -1.05
     Flavoring
    -0.94
    tera
    -0.90
    »Ĵ
    -0.86
    quished
    -0.81
    actionDate
    -0.81
    undai
    -0.80
    olphins
    -0.79
     |--
    -0.79
    URES
    -0.78
    POSITIVE LOGITS
    's
    1.28
    ÃŃs
    0.95
    ´
    0.94
     liking
    0.90
    \'
    0.89
     owned
    0.86
    hood
    0.84
    `
    0.83
     versus
    0.78
     signature
    0.78
    Activations Density 5.868%

    No Known Activations