© 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. 16374
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and bodily sensations

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing physical interactions and body language

    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
    iculture
    -0.74
    Introduced
    -0.72
     mathemat
    -0.70
     redes
    -0.66
     compe
    -0.63
    Independent
    -0.63
     pressures
    -0.62
    anship
    -0.61
     facult
    -0.61
    Recomm
    -0.60
    POSITIVE LOGITS
     his
    1.14
     hers
    1.09
     her
    1.06
    his
    1.05
     my
    0.87
    him
    0.83
     forehead
    0.83
     cheeks
    0.83
    His
    0.79
     clenched
    0.78
    Activations Density 0.190%

    No Known Activations