© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 10453
    Prev
    Next
    INDEX
    Explanations

    numerical counts or scores

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counting or summing numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directions
    -0.63
    rugged
    -0.60
    ubes
    -0.60
    ured
    -0.57
    Prin
    -0.57
    ented
    -0.57
     resistant
    -0.57
     conditioned
    -0.56
    designed
    -0.56
     Enhancement
    -0.55
    POSITIVE LOGITS
     tally
    3.78
     tallied
    1.94
     totals
    1.61
     count
    1.55
     reckoning
    1.33
     counting
    1.32
     ledger
    1.31
     recount
    1.19
     counted
    1.07
     toll
    1.06
    Activations Density 0.013%

    No Known Activations