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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20907
    Prev
    Next
    INDEX
    Explanations

    mentions of repeated patterns or processes

    oai_token-act-pair · gpt-3.5-turbo

    the concept of cycles and cyclical patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orage
    -0.88
    urion
    -0.84
    inez
    -0.79
    agar
    -0.76
    sburgh
    -0.71
    imus
    -0.71
    amina
    -0.70
    anooga
    -0.69
    ritz
    -0.68
    anamo
    -0.66
    POSITIVE LOGITS
     repeats
    0.94
     cycle
    0.88
     erg
    0.83
    cles
    0.82
     repeating
    0.78
    dayName
    0.74
    back
    0.74
     repeat
    0.73
    ogenesis
    0.70
     alternating
    0.69
    Activations Density 0.074%

    No Known Activations