© 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. 7-RES-JB
    11. 13580
    Prev
    Next
    INDEX
    Explanations

    the word "guess" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guess" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.81
    contained
    -0.80
    elight
    -0.74
    rupulous
    -0.73
    tha
    -0.71
    quished
    -0.71
    iterranean
    -0.71
    annis
    -0.70
    ksh
    -0.69
    Dialogue
    -0.67
    POSITIVE LOGITS
     guesses
    1.14
     guess
    0.91
     guessed
    0.86
     guessing
    0.85
     incorrectly
    0.76
     beforehand
    0.75
    ariat
    0.73
     Guess
    0.72
     correctly
    0.69
     how
    0.66
    Activations Density 0.024%

    No Known Activations