© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 2418
    Prev
    Next
    INDEX
    Explanations

    **names** of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their associated actions or events

    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
    ardless
    -1.07
    sburgh
    -0.91
    tyard
    -0.78
    oker
    -0.76
    tsky
    -0.76
    enegger
    -0.76
    ISION
    -0.75
    piracy
    -0.72
    ounty
    -0.71
    DCS
    -0.71
    POSITIVE LOGITS
    bits
    0.91
     Amin
    0.91
     Palestin
    0.79
    xes
    0.76
     hop
    0.75
     abduct
    0.75
     hops
    0.73
    fixes
    0.71
     unden
    0.70
    atis
    0.70
    Activations Density 0.013%

    No Known Activations