© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speculate"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speculate" and its variants, indicating discussions about uncertainty or conjecture

    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
    tha
    -0.79
    nea
    -0.77
    vin
    -0.75
    nce
    -0.75
    ne
    -0.70
    breaking
    -0.67
    mar
    -0.67
    onder
    -0.66
    war
    -0.66
    este
    -0.65
    POSITIVE LOGITS
     conject
    0.90
    acebook
    0.86
    atively
    0.85
     speculate
    0.84
     conjecture
    0.77
     guesses
    0.76
    sonian
    0.73
     speculated
    0.72
     theor
    0.70
     pools
    0.70
    Activations Density 0.016%

    No Known Activations