© 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. 6-RES-JB
    11. 9688
    Prev
    Next
    INDEX
    Explanations

    terms and discussions related to gun control

    oai_token-act-pair · gpt-3.5-turbo

    terms related to firearms and gun control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eff
    -0.73
    UTC
    -0.72
     Strawberry
    -0.71
    hap
    -0.71
     Hort
    -0.70
    atta
    -0.68
     Archdemon
    -0.68
    hiba
    -0.68
     Seym
    -0.67
    akuya
    -0.67
    POSITIVE LOGITS
    powder
    1.42
     guns
    1.07
     salute
    0.92
     traffickers
    0.91
     gun
    0.88
     violence
    0.87
    smith
    0.86
    boats
    0.84
     confisc
    0.83
     barrel
    0.83
    Activations Density 0.029%

    No Known Activations