© 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. 9-RES-JB
    11. 11122
    Prev
    Next
    INDEX
    Explanations

    words related to genetic mutations or alterations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mutilation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯¯
    -0.66
     Defenders
    -0.64
     park
    -0.64
    OUGH
    -0.62
    boarding
    -0.62
    board
    -0.61
     Fellow
    -0.61
     ours
    -0.60
     Standing
    -0.60
     Fulton
    -0.59
    POSITIVE LOGITS
    iple
    1.19
    agen
    1.14
    ually
    1.11
    ilated
    1.07
    ilation
    1.07
    atis
    1.06
    iny
    1.03
    ations
    0.96
    agi
    0.93
    reating
    0.92
    Activations Density 0.025%

    No Known Activations