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. 8-RES-JB
    6. 1510
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bir" or its variations, indicating a focus on birther-related topics

    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
    eur
    -0.76
     Tune
    -0.67
    afort
    -0.63
     Marino
    -0.59
     nomine
    -0.59
    Unit
    -0.57
    EMBER
    -0.57
    ORED
    -0.56
     Slug
    -0.56
     Ukrain
    -0.56
    POSITIVE LOGITS
    mingham
    1.25
    thing
    1.15
    git
    1.08
    ging
    1.06
    gement
    1.04
    keley
    1.03
    acial
    1.01
    ges
    1.01
    ged
    1.00
    gments
    0.99
    Activations Density 0.061%

    No Known Activations