© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20293
    Prev
    Next
    INDEX
    Explanations

    phrases related to repeated actions or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    patterns of repetition and redundancy in actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Thumbnail
    -0.85
    arton
    -0.70
    erville
    -0.70
    allery
    -0.67
    uci
    -0.66
    orthy
    -0.66
    ogun
    -0.66
    士
    -0.66
    ahime
    -0.66
    qualified
    -0.65
    POSITIVE LOGITS
     Eventually
    1.34
     until
    1.32
    until
    1.25
     endlessly
    1.24
     till
    1.24
     alternating
    1.21
    Eventually
    1.20
     futile
    1.09
     incess
    1.08
     repetition
    1.06
    Activations Density 0.603%

    No Known Activations