© 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. 10-RES-JB
    11. 3197
    Prev
    Next
    INDEX
    Explanations

    expressions relating to feelings or personal thoughts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.69
    etts
    -0.68
    ullivan
    -0.68
     Delicious
    -0.68
     Suppose
    -0.63
    ROR
    -0.63
    ceivable
    -0.60
    Scroll
    -0.58
    tainment
    -0.58
     Celeb
    -0.58
    POSITIVE LOGITS
     unfairly
    0.86
     obligated
    0.86
     burden
    0.85
     betrayed
    0.85
     owed
    0.82
     inadequ
    0.82
     slipping
    0.75
     missing
    0.75
     stepping
    0.74
     compelled
    0.73
    Activations Density 0.140%

    No Known Activations