© 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 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. 23996
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement and crime

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    igmatic
    -0.98
    uously
    -0.83
     TAMADRA
    -0.80
     Parables
    -0.76
    iqueness
    -0.75
    href
    -0.71
    agger
    -0.70
    nces
    -0.69
    forth
    -0.69
    yip
    -0.68
    POSITIVE LOGITS
     firefighter
    0.85
     administrative
    0.84
     firefighters
    0.84
     paramilitary
    0.81
     judiciary
    0.79
     paramed
    0.79
     nurses
    0.79
     DEA
    0.78
     prosecutors
    0.78
     prosecut
    0.76
    Activations Density 0.274%

    No Known Activations