© 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. 1-RES-JB
    11. 24037
    Prev
    Next
    INDEX
    Explanations

    scientific and technological terms

    oai_token-act-pair · gpt-3.5-turbo

    significant events or concepts related to finance and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scenes
    -0.78
    Vers
    -0.68
     wishes
    -0.65
    dos
    -0.58
     Sorceress
    -0.56
     Patriarch
    -0.54
     Winds
    -0.54
     Awakens
    -0.54
     Supports
    -0.52
    orig
    -0.51
    POSITIVE LOGITS
    urated
    0.74
    arij
    0.67
    bley
    0.67
    wcs
    0.66
    ometimes
    0.65
    roud
    0.62
    cedented
    0.61
    wikipedia
    0.61
    enced
    0.61
    kaya
    0.61
    Activations Density 4.272%

    No Known Activations