© 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. 4409
    Prev
    Next
    INDEX
    Explanations

    dates related to legal decisions

    oai_token-act-pair · gpt-3.5-turbo

    specific legislative actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     paradise
    -0.73
     loves
    -0.71
     Travels
    -0.71
    animate
    -0.69
     sleeps
    -0.67
    uv
    -0.67
    die
    -0.66
    Die
    -0.62
     Syndrome
    -0.61
     selfies
    -0.61
    POSITIVE LOGITS
     unanimously
    0.91
     Grassley
    0.90
     ratification
    0.85
    displayText
    0.84
     bipartisan
    0.83
     unanimous
    0.81
     deliber
    0.80
     authorizing
    0.80
     Oversight
    0.79
     approving
    0.78
    Activations Density 0.772%

    No Known Activations