© 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. 8-RES-JB
    11. 11255
    Prev
    Next
    INDEX
    Explanations

    terms related to cycles

    oai_token-act-pair · gpt-3.5-turbo

    references to cycles and cyclical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inez
    -0.98
    orage
    -0.89
    essors
    -0.86
    alty
    -0.81
    imus
    -0.80
    animous
    -0.78
    anamo
    -0.77
    asketball
    -0.77
    amina
    -0.77
     Aires
    -0.75
    POSITIVE LOGITS
     cycle
    1.07
     erg
    0.91
    cycle
    0.87
     cycles
    0.87
    cles
    0.87
     Cycle
    0.85
     repeats
    0.81
    cycles
    0.81
    chron
    0.75
     alternating
    0.74
    Activations Density 0.032%

    No Known Activations