© 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. 9-RES-JB
    11. 15622
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    complex symbols and special character sequences that may indicate legal or regulatory terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drawn
    -0.71
     UD
    -0.68
     Freed
    -0.67
     vulner
    -0.67
     mitochond
    -0.66
     further
    -0.66
     Mush
    -0.65
     Lob
    -0.64
     leaps
    -0.64
     detached
    -0.62
    POSITIVE LOGITS
    axis
    0.93
    same
    0.92
    ï¸ı
    0.91
    actual
    0.90
    ecycle
    0.89
    vernment
    0.89
    orld
    0.88
    amily
    0.88
    #$
    0.87
     Klux
    0.87
    Activations Density 0.083%

    No Known Activations