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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19429
    Prev
    Next
    INDEX
    Explanations

    instances of the word "repeated"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeated"

    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
    istry
    -0.84
    emed
    -0.70
    wit
    -0.69
    istics
    -0.69
    ellow
    -0.69
    ampunk
    -0.68
    emaker
    -0.65
    sie
    -0.65
    HHHH
    -0.65
    istical
    -0.64
    POSITIVE LOGITS
     repetition
    0.96
     playthrough
    0.89
     repeats
    0.89
     occurrences
    0.88
     rounds
    0.85
     repeated
    0.83
     repeating
    0.83
     subsequ
    0.80
     repeat
    0.79
     offenders
    0.78
    Activations Density 0.013%

    No Known Activations