© 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. 8-RES-JB
    11. 1164
    Prev
    Next
    INDEX
    Explanations

    actions related to crimes or legal issues

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to crime and assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.76
    season
    -0.75
    DragonMagazine
    -0.75
    pure
    -0.69
    doi
    -0.67
    DX
    -0.66
    lux
    -0.66
    hist
    -0.65
    Games
    -0.65
    microsoft
    -0.63
    POSITIVE LOGITS
     subsequently
    1.12
     then
    1.02
     injuring
    0.96
     THEN
    0.93
     subsequent
    0.92
     proceeded
    0.87
     ensuing
    0.87
     stole
    0.86
     detonated
    0.86
     alleges
    0.85
    Activations Density 0.232%

    No Known Activations