© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 11909
    Prev
    Next
    INDEX
    Explanations

    references to crime, trials, legal proceedings, and justice

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crime and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [_
    -0.82
    éĹĺ
    -0.80
     whilst
    -0.78
     partName
    -0.77
     onwards
    -0.76
     ®
    -0.73
    IRE
    -0.73
    qus
    -0.73
    hm
    -0.71
    folio
    -0.71
    POSITIVE LOGITS
     Trayvon
    1.39
     KKK
    1.33
     Guantanamo
    1.32
     Confederate
    1.30
     gunman
    1.24
     Klan
    1.23
     Bundy
    1.22
     Watergate
    1.21
     NYPD
    1.20
     Tsarnaev
    1.18
    Activations Density 0.654%

    No Known Activations