© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18809
    Prev
    Next
    INDEX
    Explanations

    references to famous music bands and magazines

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Rolling Stone" magazine and its related subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.08
    sense
    -0.99
    ancies
    -0.87
    flies
    -0.87
    icult
    -0.86
    lessly
    -0.83
    erate
    -0.83
    trak
    -0.80
    ilian
    -0.78
    ancy
    -0.78
    POSITIVE LOGITS
     Stones
    0.89
     Britann
    0.74
     Jub
    0.73
     Square
    0.70
     negatives
    0.69
     Thatcher
    0.68
     Papers
    0.66
     Clubs
    0.65
    ãĤ¦ãĤ¹
    0.65
     Peoples
    0.64
    Activations Density 0.084%

    No Known Activations