© 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. 0-RES-JB
    11. 1987
    Prev
    Next
    INDEX
    Explanations

    names of specific people and places

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heastern
    -0.84
     ATI
    -0.83
    xit
    -0.77
    armor
    -0.73
    flush
    -0.70
     rack
    -0.69
    Abyss
    -0.68
     Acer
    -0.68
    igh
    -0.66
     Sect
    -0.66
    POSITIVE LOGITS
     Winn
    3.13
     Rosa
    1.60
     Pascal
    1.45
     Mandela
    1.40
     Belle
    1.28
     Pablo
    1.23
    wik
    1.15
     Poc
    1.14
     Garry
    1.10
     ML
    1.08
    Activations Density 0.063%

    No Known Activations