© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 11268
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to certain characters or individuals with the last name "Shepard."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Shepard" and related variants

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

    No Comments

    Negative Logits
    tc
    -0.90
    phthal
    -0.81
    ohyd
    -0.77
    opathic
    -0.77
    emetery
    -0.76
    TABLE
    -0.76
    essional
    -0.73
    oky
    -0.72
    ocytes
    -0.72
    culus
    -0.71
    POSITIVE LOGITS
     Shepard
    1.02
    sburg
    0.91
     Andromeda
    0.83
     Shepherd
    0.78
    bilt
    0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
     achie
    0.72
     Haas
    0.72
    pard
    0.71
     SR
    0.71
    Activations Density 0.023%

    No Known Activations