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. 15231
    Prev
    Next
    INDEX
    Explanations

    phrases expressing doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or enthusiasm

    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
    quickShipAvailable
    -0.77
    ioned
    -0.71
    unal
    -0.68
    cephal
    -0.62
    surprisingly
    -0.62
    etheless
    -0.62
    actionDate
    -0.61
    minist
    -0.61
    ãĤ§
    -0.60
    Mand
    -0.60
    POSITIVE LOGITS
    '."
    1.22
    .'"
    1.18
    '"
    1.16
    ',"
    1.14
    ,'"
    1.11
    !'"
    1.10
    .")
    1.04
    ?'"
    1.04
    ãĢı
    1.00
    ?".
    0.93
    Activations Density 0.224%

    No Known Activations