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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 18836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong assertion or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    assertive phrases or statements that emphasize necessity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     admittedly
    -0.76
     rightfully
    -0.73
     optionally
    -0.71
     inevitably
    -0.68
     likewise
    -0.67
     incidentally
    -0.67
     Leone
    -0.66
     thence
    -0.65
     presumably
    -0.65
     equally
    -0.64
    POSITIVE LOGITS
    estate
    0.81
    hing
    0.81
    hin
    0.80
    hig
    0.72
    Buff
    0.71
    rawdownloadcloneembedreportprint
    0.71
    natureconservancy
    0.70
    tin
    0.68
    uyomi
    0.68
    illon
    0.68
    Activations Density 0.272%

    No Known Activations