© 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. 8-RES-JB
    11. 6065
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning the certainty or validity of statements or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rote
    -0.80
    ãĥ´ãĤ¡
    -0.71
    "},
    -0.64
    rite
    -0.61
    wash
    -0.59
    andem
    -0.58
    oos
    -0.58
     "+
    -0.58
    nox
    -0.56
    arie
    -0.55
    POSITIVE LOGITS
     depends
    1.43
     varies
    1.13
     remains
    1.12
     depended
    0.91
     or
    0.86
     lies
    0.75
     hinges
    0.73
     Regardless
    0.70
     versus
    0.68
     differs
    0.67
    Activations Density 0.324%

    No Known Activations