© 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. 4-RES-JB
    11. 10124
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular individual named Johnson

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Johnson."

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

    No Comments

    Negative Logits
     fuse
    -0.71
    rises
    -0.68
    mble
    -0.68
    nces
    -0.67
    PDATE
    -0.67
     amplification
    -0.66
    peria
    -0.63
     clearing
    -0.63
     downside
    -0.62
    thur
    -0.62
    POSITIVE LOGITS
    Johnson
    1.07
    stown
    1.04
     Controls
    0.98
     Johnson
    0.97
    ston
    0.95
    STON
    0.92
    ota
    0.88
    son
    0.82
    inson
    0.80
     Skywalker
    0.80
    Activations Density 0.011%

    No Known Activations