© 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. 8-RES-JB
    11. 22534
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports regular seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to regular season sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.66
    =-=-=-=-=-=-=-=-
    -0.66
    Sov
    -0.64
     Instruments
    -0.64
     Psychiat
    -0.63
    zos
    -0.63
     Bulgar
    -0.63
    ryu
    -0.62
    Companies
    -0.62
    200000
    -0.62
    POSITIVE LOGITS
     season
    1.19
    season
    1.13
     offseason
    0.92
     seasons
    0.87
     league
    0.85
     Season
    0.83
    izational
    0.81
    iors
    0.81
     playoffs
    0.79
     postseason
    0.79
    Activations Density 0.048%

    No Known Activations