© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 16065
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Ba"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ba" with varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wise
    -0.86
    otle
    -0.82
    lessly
    -0.78
    LAND
    -0.72
    ments
    -0.72
    lich
    -0.70
    mented
    -0.68
    aments
    -0.68
    geist
    -0.67
    detail
    -0.67
    POSITIVE LOGITS
    uble
    1.03
    iley
    1.03
    atar
    0.97
    iting
    0.94
    ison
    0.89
    uman
    0.89
    umann
    0.85
    plin
    0.83
    ilee
    0.83
    ñ
    0.81
    Activations Density 0.040%

    No Known Activations