© 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. 3-RES-JB
    11. 1564
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement or police activities

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    topic
    -0.97
    ayne
    -0.87
    ranged
    -0.79
    Pad
    -0.78
    reality
    -0.77
    ital
    -0.76
    Hop
    -0.75
    itus
    -0.73
    umen
    -0.72
    pine
    -0.71
    POSITIVE LOGITS
     stationed
    0.85
     Polic
    0.78
     policemen
    0.75
     corrid
    0.74
     barric
    0.70
     blot
    0.68
    zzi
    0.65
     undert
    0.64
     guarding
    0.64
    /
    0.64
    Activations Density 0.014%

    No Known Activations