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. 7-RES-JB
    6. 23279
    Prev
    Next
    INDEX
    Explanations

    instances of 'speaking at' phrases, especially when the speaker is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at [number]" in relation to events or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thri
    -0.73
     benefited
    -0.73
    gans
    -0.70
    chrome
    -0.65
    ratulations
    -0.64
    Lens
    -0.63
    aceutical
    -0.63
     belong
    -0.62
    Owner
    -0.62
    Connector
    -0.61
    POSITIVE LOGITS
     halftime
    1.21
     least
    1.11
    rium
    0.92
    onement
    0.92
    yp
    0.91
     conferences
    0.89
     midday
    0.88
     CES
    0.88
    rial
    0.83
     midnight
    0.82
    Activations Density 0.164%

    No Known Activations