© 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. 20592
    Prev
    Next
    INDEX
    Explanations

    the concept of repetition or doing something again

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "repeat" and its variations

    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
    sie
    -0.77
    ramid
    -0.75
    uana
    -0.73
    ffe
    -0.72
    esthetic
    -0.69
    atana
    -0.68
    uay
    -0.68
    erie
    -0.66
    hoff
    -0.66
    hattan
    -0.66
    POSITIVE LOGITS
     repeat
    1.00
    repeat
    0.97
     repeats
    0.94
     offenders
    0.93
     offender
    0.89
     playthrough
    0.84
     repeating
    0.83
    ability
    0.79
     Repeat
    0.78
    lly
    0.78
    Activations Density 0.021%

    No Known Activations