© 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. 2-RES-JB
    11. 1434
    Prev
    Next
    INDEX
    Explanations

    the word "cycle" in various contexts, potentially related to recurring patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cycle" and its related forms, indicating a focus on recurring themes or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essors
    -0.80
    inez
    -0.78
    alties
    -0.76
    roit
    -0.74
    unicip
    -0.74
    azeera
    -0.74
    ever
    -0.74
    affer
    -0.72
    urion
    -0.72
    orage
    -0.72
    POSITIVE LOGITS
     cycle
    1.23
     Cycle
    1.14
    cycles
    1.09
    cycle
    1.09
     cycles
    1.09
     CY
    0.84
     Britann
    0.78
     erg
    0.77
     repeats
    0.74
    cles
    0.73
    Activations Density 0.012%

    No Known Activations