© 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. 11-RES-JB
    11. 23221
    Prev
    Next
    INDEX
    Explanations

    keywords associated with ability or capability

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "able" indicating capability or possibility

    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
     Bots
    -0.62
     Deer
    -0.61
    THING
    -0.57
    bour
    -0.55
    ccording
    -0.54
     Rising
    -0.54
     Nose
    -0.54
    Lens
    -0.52
    ELD
    -0.52
    assault
    -0.51
    POSITIVE LOGITS
     to
    1.07
    bodied
    0.98
     afford
    0.84
     bod
    0.78
     withstand
    0.76
     ta
    0.76
    ioned
    0.72
     communicate
    0.72
     replicate
    0.70
    ãĥīãĥ©
    0.70
    Activations Density 0.055%

    No Known Activations