Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4358
    Prev
    Next
    INDEX
    Explanations

    personal names

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly politicians or historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iband
    -0.96
    fman
    -0.89
    istani
    -0.87
    keley
    -0.81
    ictionary
    -0.80
    acea
    -0.80
    adesh
    -0.77
    wide
    -0.75
    uckland
    -0.75
    ationally
    -0.75
    POSITIVE LOGITS
     Dup
    1.20
     Gou
    1.20
     Hollande
    1.19
     Philippe
    1.18
     Bou
    1.17
     Blanc
    1.16
     Ré
    1.16
     Gir
    1.13
     Laurent
    1.12
     Mé
    1.09
    Activations Density 0.063%

    No Known Activations