© 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. 594
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hesitancy or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and phrases indicating unlikelihood or impossibility

    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
    ashtra
    -0.77
    iferation
    -0.62
    usion
    -0.60
    espie
    -0.59
    geries
    -0.59
    angered
    -0.59
    ousy
    -0.59
    ructose
    -0.57
    aston
    -0.57
    pell
    -0.56
    POSITIVE LOGITS
    etheless
    1.07
     nonetheless
    0.94
     guarantee
    0.81
     necessarily
    0.75
     guarantees
    0.75
    until
    0.72
     until
    0.72
     enough
    0.66
     quite
    0.64
    `.
    0.63
    Activations Density 0.314%

    No Known Activations