© 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. 1960
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "coincidence"

    oai_token-act-pair · gpt-3.5-turbo

    references to coincidences and the concept of coincidence in various contexts

    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
    ħĭ
    -0.83
    ä¸Ń
    -0.79
    bern
    -0.75
    itsch
    -0.72
    grave
    -0.71
    anamo
    -0.69
    abit
    -0.69
    ogy
    -0.69
    ©¶æ
    -0.69
    ocyte
    -0.65
    POSITIVE LOGITS
     coincidence
    1.31
     coinc
    1.23
    idental
    0.91
    identally
    0.86
     coincide
    0.81
     occurrence
    0.78
    istically
    0.77
    uate
    0.77
     occurrences
    0.76
     anomaly
    0.73
    Activations Density 0.009%

    No Known Activations