© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 5622
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "criminal" and related terms indicating illegal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -1.06
     Remastered
    -0.83
    metry
    -0.80
    daq
    -0.80
    pread
    -0.79
    chell
    -0.78
     Pixie
    -0.76
    mates
    -0.76
     Canaver
    -0.76
    pler
    -0.76
    POSITIVE LOGITS
    ized
    1.11
    izes
    1.01
    ization
    1.00
     justice
    0.99
     prosecutions
    0.97
     sanction
    0.95
     prosecution
    0.95
    ised
    0.93
     enterprises
    0.91
     sanctions
    0.91
    Activations Density 0.034%

    No Known Activations