© 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. 1-RES-JB
    11. 24205
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Bradley."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Bradley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fecture
    -0.82
    selection
    -0.74
    display
    -0.71
    atom
    -0.71
    cient
    -0.68
    Crime
    -0.67
    chrom
    -0.66
    IDENT
    -0.66
    trigger
    -0.66
    displayText
    -0.66
    POSITIVE LOGITS
     Bradley
    1.46
     Manning
    1.12
     Johnston
    0.86
     Wiggins
    0.83
     Edwards
    0.81
     Porter
    0.78
     Pa
    0.76
     Sachs
    0.76
     Bros
    0.75
     Kingston
    0.74
    Activations Density 0.002%

    No Known Activations