Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 24099
    Prev
    Next
    INDEX
    Explanations

    numerical data formatted in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to counts or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.81
    lass
    -0.80
    Reviewer
    -0.71
    shape
    -0.71
    amaru
    -0.70
    inet
    -0.70
    folk
    -0.69
    inav
    -0.68
    merce
    -0.68
    aban
    -0.68
    POSITIVE LOGITS
     fewer
    1.02
     consecutive
    0.92
     additional
    0.84
     distinct
    0.84
     percent
    0.81
     apiece
    0.80
     feet
    0.76
     degrees
    0.75
    uous
    0.75
     million
    0.75
    Activations Density 0.157%

    No Known Activations