© 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. 8-RES-JB
    11. 17659
    Prev
    Next
    INDEX
    Explanations

    mentions of periods of time, such as "20-year period" or "centuries."

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    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
    minster
    -0.75
    Thumbnail
    -0.60
    venth
    -0.59
    oya
    -0.58
    ãĥ¥
    -0.57
    apsed
    -0.57
    eret
    -0.56
    ãģł
    -0.55
    UF
    -0.54
    ener
    -0.54
    POSITIVE LOGITS
     namely
    0.86
     please
    0.84
     wherein
    0.84
     including
    0.81
     huh
    0.81
     preferably
    0.74
     comprising
    0.70
     respectively
    0.69
     culminating
    0.69
     irrespective
    0.69
    Activations Density 0.328%

    No Known Activations