© 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. 7-RES-JB
    11. 23577
    Prev
    Next
    INDEX
    Explanations

    specific times written in the format of "X a.m." or "X p.m."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    livious
    -0.71
    acebook
    -0.67
    enhagen
    -0.64
     Answers
    -0.64
    ebin
    -0.64
    abwe
    -0.63
    ahime
    -0.62
    ylum
    -0.62
     Annotations
    -0.62
    inous
    -0.62
    POSITIVE LOGITS
     month
    0.87
    versions
    0.85
     week
    0.84
     weekday
    0.81
    pm
    0.79
     dozen
    0.79
     decade
    0.77
     cycle
    0.77
    iren
    0.75
     midnight
    0.74
    Activations Density 0.023%

    No Known Activations