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. 3-RES-JB
    6. 18766
    Prev
    Next
    INDEX
    Explanations

    numerical values related to various measurements or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly related to quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nels
    -0.93
    orate
    -0.82
    alez
    -0.78
    lict
    -0.76
    inez
    -0.74
    inges
    -0.74
    essen
    -0.74
    nell
    -0.74
    oses
    -0.73
    querque
    -0.72
    POSITIVE LOGITS
     ILCS
    0.98
     MHz
    0.93
    æ©Ł
    0.81
    MHz
    0.76
    SourceFile
    0.72
    989
    0.70
    490
    0.67
     meters
    0.66
    576
    0.66
     feet
    0.66
    Activations Density 0.041%

    No Known Activations