© 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. 11-RES-JB
    11. 6425
    Prev
    Next
    INDEX
    Explanations

    terms related to sports

    oai_token-act-pair · gpt-3.5-turbo

    references to various sports and sporting events

    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
    ignt
    -0.76
     Passage
    -0.71
     Bride
    -0.66
     Khe
    -0.63
     Prompt
    -0.59
     Centauri
    -0.55
     Sunshine
    -0.55
     Declaration
    -0.55
     Dispatch
    -0.55
     chords
    -0.54
    POSITIVE LOGITS
    sw
    1.57
    scar
    1.45
    sc
    1.12
    nell
    1.04
    ive
    0.98
    nels
    0.95
    manship
    0.94
    saf
    0.92
    bike
    0.91
    spe
    0.90
    Activations Density 0.038%

    No Known Activations