© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13639
    Prev
    Next
    INDEX
    Explanations

    technical instructions or explanations, potentially related to physical actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to visual art and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thous
    -1.02
     Byrd
    -0.84
     withd
    -0.84
     oun
    -0.80
     Kaw
    -0.79
     bundled
    -0.77
     Kau
    -0.77
     Gott
    -0.76
     Bai
    -0.76
    ¿½
    -0.76
    POSITIVE LOGITS
    terrorism
    0.94
    ruption
    0.91
    corruption
    0.91
    iculture
    0.89
    asis
    0.84
    urrency
    0.84
    reality
    0.82
    scene
    0.81
    content
    0.81
    rot
    0.81
    Activations Density 0.149%

    No Known Activations