© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, particularly in contexts indicating introspection or evaluation of feelings and actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating personal identity and relationships

    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
     incorpor
    -0.71
     feedback
    -0.71
     confir
    -0.68
     compressor
    -0.64
    arthed
    -0.63
     differentiation
    -0.63
    interstitial
    -0.60
    ipedia
    -0.60
     anecdotal
    -0.60
     citations
    -0.58
    POSITIVE LOGITS
     truly
    1.05
     owe
    1.01
     ought
    0.98
     deserve
    0.97
     scarcely
    0.93
     alone
    0.92
     unworthy
    0.92
     dare
    0.91
    must
    0.89
     desperately
    0.89
    Activations Density 0.399%

    No Known Activations