© 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. 0-RES-JB
    11. 11435
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific references to people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "whoever."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brief
    -0.63
    ell
    -0.59
     graph
    -0.59
     Depth
    -0.57
     recently
    -0.56
     feature
    -0.56
    ´
    -0.55
     Introduced
    -0.55
     features
    -0.55
    erv
    -0.54
    POSITIVE LOGITS
     whoever
    3.59
     Whoever
    2.64
    Whoever
    2.52
    omever
    2.25
     whichever
    2.11
     whatever
    1.76
    whatever
    1.73
     wherever
    1.55
     anybody
    1.52
    ichever
    1.50
    Activations Density 0.010%

    No Known Activations