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. 8043
    Prev
    Next
    INDEX
    Explanations

    phrases related to key elements or components

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with essential nutrients and their importance

    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
    renheit
    -0.82
    isSpecialOrderable
    -0.73
    Roy
    -0.73
    owler
    -0.68
    creen
    -0.68
    ammers
    -0.68
    rows
    -0.68
    ammad
    -0.68
    pload
    -0.66
    BU
    -0.65
    POSITIVE LOGITS
    iary
    0.95
     ingredient
    0.92
    isin
    0.85
     components
    0.84
    izing
    0.83
     organs
    0.83
    ised
    0.82
    ogical
    0.82
     component
    0.80
    ogy
    0.78
    Activations Density 0.036%

    No Known Activations