© 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. 3-RES-JB
    11. 16153
    Prev
    Next
    INDEX
    Explanations

    locations or terms related to specific electoral events and results

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Champaign and its related electoral activities

    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
    isphere
    -0.91
    icum
    -0.81
    ¶ħ
    -0.76
    itans
    -0.76
    itan
    -0.75
    seys
    -0.69
    ora
    -0.68
    brate
    -0.67
    atsuki
    -0.67
    ascript
    -0.67
    POSITIVE LOGITS
    ski
    0.82
    sburgh
    0.81
    aign
    0.78
    eal
    0.76
    ablishment
    0.75
    iard
    0.75
    spr
    0.72
    allery
    0.69
    eh
    0.69
    Sov
    0.68
    Activations Density 0.032%

    No Known Activations