© 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. 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. 18398
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or criminal behavior

    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
    emonium
    -0.52
     anecd
    -0.52
    nesday
    -0.50
    ivating
    -0.49
    icion
    -0.49
     Cosponsors
    -0.48
    orously
    -0.48
     disclaimer
    -0.48
    FAQ
    -0.47
     Gutenberg
    -0.46
    POSITIVE LOGITS
     raping
    0.52
     sexually
    0.46
     psychotic
    0.46
     breast
    0.45
     sexual
    0.45
     genitals
    0.45
     pleasure
    0.44
     gang
    0.43
     compuls
    0.43
    thood
    0.43
    Activations Density 1.854%

    No Known Activations