© 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. 7-RES-JB
    11. 3079
    Prev
    Next
    INDEX
    Explanations

    mentions of specific historical figures and writings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CEO
    -0.93
     paycheck
    -0.86
    jobs
    -0.84
     CEO
    -0.82
    SHARE
    -0.81
     skinny
    -0.75
     CEOs
    -0.73
     cybersecurity
    -0.73
     Obamacare
    -0.72
     millennials
    -0.72
    POSITIVE LOGITS
     interpol
    1.13
     histor
    1.13
    ibliography
    1.06
     textual
    1.05
     quotations
    1.03
     chronological
    1.02
    cyclopedia
    1.01
     Tolkien
    1.00
     extant
    0.99
    olkien
    0.98
    Activations Density 1.124%

    No Known Activations