© 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. 12-RES-JB
    11. 3386
    Prev
    Next
    INDEX
    Explanations

    statistical data and survey results

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statistical data and percentages related to polling results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    advertisement
    -0.81
    uality
    -0.80
    agascar
    -0.75
    izzle
    -0.73
    iasis
    -0.73
    isoft
    -0.72
    skirts
    -0.72
    asar
    -0.72
    Appearances
    -0.70
    âĶĢ
    -0.70
    POSITIVE LOGITS
     Likely
    1.31
     independents
    1.28
     Republicans
    1.23
     Democrats
    1.19
     respondents
    1.19
     voters
    1.17
     registered
    1.15
     likely
    1.13
     GOP
    1.04
     Americans
    1.03
    Activations Density 0.139%

    No Known Activations