© 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. 9-RES-JB
    11. 15513
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, particularly mentioning "finals" and "semi-finals"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "final" and its variants in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grow
    -0.82
    hart
    -0.78
    ravings
    -0.74
    afort
    -0.73
    resp
    -0.71
    atech
    -0.70
    facts
    -0.70
    velt
    -0.69
    lein
    -0.69
    travel
    -0.69
    POSITIVE LOGITS
     berth
    0.97
    ists
    0.95
     qualifier
    0.94
     podium
    0.91
     showdown
    0.90
     curtain
    0.86
     matchup
    0.86
     standings
    0.83
     winners
    0.83
     semifinals
    0.83
    Activations Density 0.056%

    No Known Activations