Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17514
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sherman"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sherman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lib
    -0.83
     morph
    -0.69
     py
    -0.69
    inary
    -0.68
    Org
    -0.66
     fo
    -0.66
     flavours
    -0.63
     doct
    -0.63
    lo
    -0.63
    porting
    -0.63
    POSITIVE LOGITS
     Sherman
    4.10
    Sher
    1.75
     Sheridan
    1.54
     Harding
    1.25
     Abrams
    1.23
     Sher
    1.21
     Patton
    1.14
     Seah
    1.11
     Berman
    1.09
     Stanton
    1.07
    Activations Density 0.015%

    No Known Activations