© 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. 6662
    Prev
    Next
    INDEX
    Explanations

    the word "coincidence."

    oai_token-act-pair · gpt-3.5-turbo

    references to coincidence and related concepts

    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
    bern
    -0.95
    artney
    -0.82
    ved
    -0.75
    ħĭ
    -0.74
    ibaba
    -0.73
    ä¸Ń
    -0.72
    grave
    -0.70
    irts
    -0.69
    emouth
    -0.69
    burgh
    -0.68
    POSITIVE LOGITS
     coincidence
    1.10
     coinc
    0.90
     occurrence
    0.86
    DragonMagazine
    0.85
     occurrences
    0.82
    ality
    0.75
     glances
    0.73
    istically
    0.73
     charm
    0.71
    idental
    0.70
    Activations Density 0.015%

    No Known Activations