© 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. 4163
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to a person named Herman

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Herman."

    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
    yrim
    -0.75
     Thumbnails
    -0.73
    uren
    -0.68
    aucus
    -0.63
    uthor
    -0.63
    ĵĺ
    -0.63
    ifter
    -0.62
    imag
    -0.61
    oward
    -0.61
    iful
    -0.61
    POSITIVE LOGITS
    n
    1.17
    nant
    0.91
    nian
    0.88
    ns
    0.85
    ni
    0.84
    ium
    0.83
    stein
    0.80
    tz
    0.79
    nis
    0.78
    cil
    0.78
    Activations Density 0.049%

    No Known Activations