© 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. 4-RES-JB
    11. 11420
    Prev
    Next
    INDEX
    Explanations

    repetitions of words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "times" indicating repetition or frequency in a text

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

    No Comments

    Negative Logits
    Reviewer
    -0.87
    uld
    -0.80
    Marginal
    -0.75
    irt
    -0.74
    oki
    -0.72
    CHAT
    -0.71
     heirs
    -0.71
    XT
    -0.70
    ITAL
    -0.70
    LCS
    -0.69
    POSITIVE LOGITS
    cale
    1.05
    manship
    0.90
    times
    0.77
     consecut
    0.75
    bp
    0.74
    hops
    0.73
    bps
    0.73
     throughout
    0.72
     Ago
    0.72
    points
    0.71
    Activations Density 0.025%

    No Known Activations