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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 547
    Prev
    Next
    INDEX
    Explanations

    numbers such as quantities, years, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantities related to sports achievements and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    react
    -0.80
    hap
    -0.79
    operator
    -0.73
    aban
    -0.72
    uffer
    -0.70
    sylv
    -0.70
    rish
    -0.70
    pose
    -0.69
    nown
    -0.67
    dit
    -0.66
    POSITIVE LOGITS
     seasons
    1.20
     championships
    1.05
    peat
    1.04
     continents
    1.03
     consecutive
    1.00
     Cups
    0.97
     stint
    0.93
     successive
    0.91
     editions
    0.90
     titles
    0.90
    Activations Density 0.134%

    No Known Activations