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. 13266
    Prev
    Next
    INDEX
    Explanations

    significant numerical figures, including percentages and quantities

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistics related to economic contributions and exports

    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
     Collider
    -0.66
    evin
    -0.64
    ↵Âł
    -0.62
    aunts
    -0.61
     proclamation
    -0.61
     Rivals
    -0.60
     jerk
    -0.60
    ffen
    -0.59
    hess
    -0.59
    timer
    -0.57
    POSITIVE LOGITS
     million
    1.19
     billion
    1.06
     thousand
    1.02
    million
    1.01
     trillion
    1.00
     crore
    0.97
     000
    0.96
     lakh
    0.93
     tonnes
    0.91
    %
    0.89
    Activations Density 0.346%

    No Known Activations