© 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. 10-RES-JB
    11. 9223
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    capital letters that likely represent names

    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
     Coral
    -0.67
     Cecil
    -0.63
     Cricket
    -0.60
     Pixar
    -0.59
     Devon
    -0.59
     Telegraph
    -0.59
     pleasure
    -0.59
     dispatch
    -0.58
     Windsor
    -0.58
     Mercury
    -0.57
    POSITIVE LOGITS
    akh
    1.10
    awar
    0.94
    abis
    0.91
    ulk
    0.91
    oub
    0.86
    issan
    0.85
    inav
    0.84
    uty
    0.84
    ı
    0.83
    ikh
    0.82
    Activations Density 0.104%

    No Known Activations