© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 8461
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to sports teams and players

    oai_token-act-pair · gpt-3.5-turbo

    references to "The" indicating the mention of specific subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    978
    -0.78
    pers
    -0.76
    antes
    -0.72
    ø
    -0.70
    bg
    -0.70
    unia
    -0.68
    rm
    -0.68
     :-)
    -0.68
    uala
    -0.67
     ®
    -0.67
    POSITIVE LOGITS
    oret
    1.14
     latter
    1.02
     league
    1.01
     rookie
    0.99
     youngest
    0.98
     reigning
    0.96
     biggest
    0.96
     rest
    0.96
     Bucs
    0.96
     Blazers
    0.95
    Activations Density 0.498%

    No Known Activations