© 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. 10-RES-JB
    11. 17428
    Prev
    Next
    INDEX
    Explanations

    words related to time periods or events, particularly the word "year" or names of seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods, particularly focusing on the current and upcoming years and seasons

    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
    umblr
    -0.74
     Journals
    -0.72
     typew
    -0.67
     ut
    -0.65
    ibur
    -0.65
     hemor
    -0.64
    omething
    -0.63
    uv
    -0.62
     fixation
    -0.62
    erate
    -0.62
    POSITIVE LOGITS
     onwards
    0.74
     edition
    0.73
    abouts
    0.72
    iversary
    0.69
     EDITION
    0.68
     Edition
    0.67
    long
    0.66
    EngineDebug
    0.65
     alone
    0.65
    cture
    0.64
    Activations Density 0.087%

    No Known Activations