© 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. 7-RES-JB
    11. 3082
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utical
    -0.74
     Canal
    -0.73
     Supplement
    -0.73
    é¾įå
    -0.72
     Improvement
    -0.71
     nutrit
    -0.70
     detrim
    -0.69
     Debate
    -0.67
     menstrual
    -0.67
     Question
    -0.66
    POSITIVE LOGITS
     explosives
    0.89
     gunmen
    0.87
    abwe
    0.85
     detonated
    0.84
     armed
    0.84
     rampage
    0.83
     motive
    0.83
     spree
    0.83
     deton
    0.82
     attackers
    0.80
    Activations Density 0.577%

    No Known Activations