© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22544
    Prev
    Next
    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sat" and its variations, likely indicating references to "Saturday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.86
    taining
    -0.80
    resent
    -0.73
    tained
    -0.73
    utenberg
    -0.72
    naire
    -0.71
    mental
    -0.71
    abwe
    -0.71
    ãģª
    -0.68
    Gaming
    -0.67
    POSITIVE LOGITS
    urn
    0.90
    yrs
    0.88
    ilda
    0.88
    chel
    0.86
    oshi
    0.85
    chell
    0.84
    omi
    0.81
    alk
    0.78
    yr
    0.77
    chers
    0.76
    Activations Density 0.009%

    No Known Activations