© 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. 20241
    Prev
    Next
    INDEX
    Explanations

    terms related to imports or trade

    oai_token-act-pair · gpt-3.5-turbo

    words related to commercial transactions or business

    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
     [|
    -0.78
    shapeshifter
    -0.70
     swipe
    -0.66
    stroke
    -0.65
    hart
    -0.64
    enegger
    -0.63
     overdue
    -0.62
     stroke
    -0.61
    ITNESS
    -0.60
    saf
    -0.60
    POSITIVE LOGITS
    por
    1.28
    ters
    0.98
    isol
    0.93
    tering
    0.91
    cia
    0.87
    andum
    0.87
    TABLE
    0.86
    porate
    0.85
    unity
    0.81
    oshenko
    0.79
    Activations Density 0.009%

    No Known Activations