© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1592
    Prev
    Next
    INDEX
    Explanations

    legal terms and criminal activities, such as charges, court proceedings, sentences, and criminal acts

    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
    744
    +0.13
    0.5%
    451
    +0.12
    0.5%
    752
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.13
    0.06
    268
    +0.12
    0.02
    471
    +0.11
    0.05
    Negative Logits
     Bree
    -0.87
    Flo
    -0.86
    sylv
    -0.86
    natureconservancy
    -0.85
    áµ
    -0.78
    Morning
    -0.78
     Forums
    -0.77
    iverse
    -0.75
    ãĤ¡
    -0.75
    Prev
    -0.75
    POSITIVE LOGITS
     indictment
    1.65
     felony
    1.57
     misdemeanor
    1.50
     charges
    1.46
     extradition
    1.43
     criminally
    1.41
     prosecution
    1.41
     indicted
    1.37
     sentencing
    1.36
     indict
    1.36
    Activations Density 4.724%

    No Known Activations