© 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 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. 2329
    Prev
    Next
    INDEX
    Explanations

    instances of text where something is done or stated publicly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "publicly" and its variations

    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
    nesota
    -0.83
    nian
    -0.83
    mble
    -0.79
     Velocity
    -0.72
    NER
    -0.70
    ners
    -0.69
     Origins
    -0.69
    wolves
    -0.68
     Upper
    -0.67
     Trem
    -0.67
    POSITIVE LOGITS
     shaming
    0.97
     humiliated
    0.93
     traded
    0.92
     funded
    0.86
     acknowledged
    0.86
     pronounce
    0.84
     proclaimed
    0.84
     humili
    0.83
     endorsed
    0.83
     denounced
    0.83
    Activations Density 0.017%

    No Known Activations