© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    the word "of" occurring in various contexts in the text

    oai_token-act-pair · gpt-3.5-turbo
    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
    cycles
    -0.81
    nels
    -0.74
    photos
    -0.71
    ··
    -0.70
     Components
    -0.67
    oons
    -0.66
    cles
    -0.64
    usky
    -0.64
    ktop
    -0.63
    asar
    -0.63
    POSITIVE LOGITS
     encouragement
    1.32
     caution
    1.11
     advice
    1.10
     wisdom
    1.08
     recommendation
    1.05
     warning
    1.00
     congratulations
    0.97
     mouth
    0.95
     condemnation
    0.93
     appreciation
    0.93
    Activations Density 0.080%

    No Known Activations