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. 1-RES-JB
    6. 19976
    Prev
    Next
    INDEX
    Explanations

    numerical values appearing in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.94
     Halls
    -0.82
    theless
    -0.73
    deen
    -0.66
     GOODMAN
    -0.65
    hower
    -0.64
    thirds
    -0.63
     Galile
    -0.62
     kitchens
    -0.61
     Rumble
    -0.60
    POSITIVE LOGITS
    icago
    0.97
    .,
    0.95
    ./
    0.82
     ........
    0.81
    ickr
    0.80
    Avg
    0.78
    hered
    0.77
    emp
    0.77
    nyder
    0.76
    iances
    0.75
    Activations Density 0.023%

    No Known Activations