© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names or locations starting or containing "Kel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, Kelley

    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
    BOOK
    -0.69
     AMERICA
    -0.69
    displayText
    -0.67
    xual
    -0.67
    CLASSIFIED
    -0.67
    Critical
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    æĦ
    -0.64
    ItemTracker
    -0.62
     incre
    -0.62
    POSITIVE LOGITS
    tering
    1.02
    seys
    1.01
    sten
    0.99
    zeb
    0.96
    sey
    0.95
     Lumpur
    0.94
    kie
    0.89
    iman
    0.88
    inda
    0.88
    ving
    0.88
    Activations Density 0.007%

    No Known Activations