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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 17166
    Prev
    Next
    INDEX
    Explanations

    mentions of different social groups or communities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connectors that emphasize relationships among elements

    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
    cules
    -0.81
    ģ«
    -0.81
    hani
    -0.73
    ONSORED
    -0.66
    inka
    -0.64
     Achievements
    -0.62
     reven
    -0.62
    Ïī
    -0.61
    zee
    -0.61
    ictive
    -0.61
    POSITIVE LOGITS
    fil
    0.70
    Lew
    0.62
    speaking
    0.60
    igham
    0.58
    fters
    0.58
    Mand
    0.58
    ãĤī
    0.58
    uyomi
    0.57
     Labrador
    0.57
    Ha
    0.57
    Activations Density 0.226%

    No Known Activations