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. 10-RES-JB
    6. 11772
    Prev
    Next
    INDEX
    Explanations

    the word "Bab" with a numerical value ranking the specificity of its context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Bab" along with its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICES
    -0.70
    VICE
    -0.68
     REPORT
    -0.65
    dfx
    -0.63
     gard
    -0.62
    ICE
    -0.61
     Eisen
    -0.60
     Realms
    -0.59
     mesh
    -0.59
    backer
    -0.58
    POSITIVE LOGITS
    cock
    1.09
    alon
    0.99
    ies
    0.95
    raham
    0.95
    acca
    0.94
    ush
    0.94
    ibilities
    0.90
    axter
    0.89
    ylon
    0.89
    iak
    0.89
    Activations Density 0.026%

    No Known Activations