© 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. 3874
    Prev
    Next
    INDEX
    Explanations

    references to specific events or legislation, particularly related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to events and policies related to DACA and WrestleMania

    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
    aer
    -0.86
    ron
    -0.81
    poon
    -0.81
    ruck
    -0.77
    raf
    -0.75
    Irish
    -0.75
    rop
    -0.75
    ror
    -0.74
     Riy
    -0.74
    rier
    -0.74
    POSITIVE LOGITS
     tremend
    0.93
     Expo
    0.84
     Reloaded
    0.76
    ingo
    0.73
     consolid
    0.71
     exporting
    0.68
     Mania
    0.68
     mosqu
    0.67
     demos
    0.66
     partName
    0.65
    Activations Density 0.021%

    No Known Activations