© 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. 10-RES-JB
    11. 2942
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events or actions

    oai_token-act-pair · gpt-3.5-turbo
    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
    Footnote
    -0.60
    Nation
    -0.59
    âĨĴ
    -0.58
    izable
    -0.57
    stood
    -0.57
    arta
    -0.57
     marker
    -0.56
     Millions
    -0.56
     spheres
    -0.54
     buckets
    -0.54
    POSITIVE LOGITS
    hes
    1.05
    wolves
    1.02
     born
    0.96
    wolf
    0.96
    abi
    0.88
     founded
    0.86
     originally
    0.85
     released
    0.84
     spotted
    0.82
     sentenced
    0.81
    Activations Density 0.115%

    No Known Activations