© 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. 10-RES-JB
    11. 16954
    Prev
    Next
    INDEX
    Explanations

    numerical patterns related to scores or statistics in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of fractions or ratios, specifically formatted as "number-number"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rom
    -0.74
     Roh
    -0.62
     prof
    -0.60
     Sik
    -0.59
     Brut
    -0.58
     festive
    -0.58
     tender
    -0.58
     Viet
    -0.57
     Mant
    -0.57
     fri
    -0.56
    POSITIVE LOGITS
    none
    1.02
    zero
    0.96
    one
    0.95
    four
    0.94
    nothing
    0.93
    ones
    0.92
    three
    0.92
    numbered
    0.91
    equal
    0.90
    seven
    0.89
    Activations Density 0.032%

    No Known Activations