© 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. 2-RES-JB
    11. 23715
    Prev
    Next
    INDEX
    Explanations

    information related to police forces or law enforcement agencies, specifically when there is an issue involving innocence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heat
    -0.72
     Habit
    -0.72
    hirt
    -0.69
    git
    -0.68
    ãĤª
    -0.67
     Extract
    -0.65
     Prediction
    -0.65
    peria
    -0.64
    study
    -0.64
    -|
    -0.63
    POSITIVE LOGITS
    NetMessage
    0.74
    ilater
    0.73
     Kelley
    0.70
     Curve
    0.70
    ieg
    0.70
     Harvey
    0.69
     Larson
    0.68
    Reviewer
    0.68
     Strikes
    0.66
     Lowry
    0.64
    Activations Density 0.000%

    No Known Activations