© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 5112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "guess"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guess" indicating speculation or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rome
    -0.70
    cler
    -0.68
     Antar
    -0.67
    vis
    -0.67
    waters
    -0.67
    roma
    -0.65
    Js
    -0.65
    andals
    -0.64
    Uncommon
    -0.64
    pling
    -0.64
    POSITIVE LOGITS
     guess
    1.49
     guesses
    1.32
     guessing
    1.14
     Guess
    1.13
     guessed
    0.99
    itial
    0.87
     interpretation
    0.75
     Leilan
    0.75
    estamp
    0.71
     excuse
    0.71
    Activations Density 0.013%

    No Known Activations