© 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. 11-RES-JB
    11. 22518
    Prev
    Next
    INDEX
    Explanations

    phrases indicating doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.74
    ipeg
    -0.74
    gencies
    -0.73
    ounters
    -0.72
    IRE
    -0.72
    tesy
    -0.67
    urses
    -0.67
    ridges
    -0.65
    hess
    -0.64
    licks
    -0.64
    POSITIVE LOGITS
     sure
    1.26
     kidding
    1.24
     ashamed
    1.21
     joking
    1.14
     advocating
    1.14
     surprised
    1.13
     exagger
    1.10
     saying
    1.06
     complaining
    1.04
     suggesting
    1.04
    Activations Density 0.070%

    No Known Activations