© 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. 7180
    Prev
    Next
    INDEX
    Explanations

    mentions of sports leagues and events

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events and related data

    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
     tomorrow
    -0.97
     tonight
    -0.89
     yesterday
    -0.77
     lately
    -0.75
     today
    -0.74
    Thursday
    -0.71
    Tuesday
    -0.71
    Wednesday
    -0.70
     recent
    -0.69
     nowadays
    -0.67
    POSITIVE LOGITS
    bernatorial
    0.97
     census
    0.81
     Census
    0.77
     edition
    0.76
     cycle
    0.70
    iversary
    0.69
    士
    0.66
     onwards
    0.63
     batch
    0.63
    road
    0.62
    Activations Density 0.250%

    No Known Activations