© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison of rates or growth between different time periods or generations

    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
     constitutionally
    -0.81
     traitor
    -0.81
     ransom
    -0.74
     incompetent
    -0.74
     inept
    -0.72
     slightest
    -0.72
     capit
    -0.70
     expired
    -0.70
     bellig
    -0.70
     swearing
    -0.69
    POSITIVE LOGITS
    Adds
    1.12
    Explore
    1.06
    Eventually
    0.93
    Researchers
    0.92
    Students
    0.92
    Growing
    0.90
    paces
    0.88
    Understanding
    0.87
    Interview
    0.86
    Working
    0.85
    Activations Density 0.543%

    No Known Activations