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. 11-RES-JB
    6. 18086
    Prev
    Next
    INDEX
    Explanations

    mentions of awards or recognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to awards and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anon
    -0.72
    tera
    -0.67
    ugg
    -0.67
    src
    -0.65
    XY
    -0.63
    hap
    -0.63
    ··
    -0.62
    ohyd
    -0.61
    tes
    -0.61
     abdom
    -0.61
    POSITIVE LOGITS
     winner
    1.17
     winners
    1.17
     nominations
    1.17
     ceremony
    1.14
     Winning
    1.07
     winning
    1.05
    winning
    1.05
     Winners
    1.04
     laure
    1.03
    Winner
    1.03
    Activations Density 0.059%

    No Known Activations