© 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. 11-RES-JB
    11. 3431
    Prev
    Next
    INDEX
    Explanations

    terms related to high-speed, high-risk, and high-volume data or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to high-risk and high-speed situations or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amera
    -0.80
    =-=-=-=-
    -0.78
    adier
    -0.75
    ̶
    -0.74
    anco
    -0.68
    isky
    -0.68
    unity
    -0.68
    anski
    -0.67
    wen
    -0.67
    reports
    -0.67
    POSITIVE LOGITS
     (>
    1.00
     earners
    0.89
     (<
    0.80
     residential
    0.74
     sporting
    0.69
     discretionary
    0.69
     industrial
    0.66
     urban
    0.66
     occupations
    0.66
     versions
    0.65
    Activations Density 0.170%

    No Known Activations