© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    positive emotional expressions and physical well-being-related words

    oai_token-act-pair · gpt-3.5-turbo

    sentences expressing emotional well-being or stability amidst challenges

    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
    âĢ
    -0.89
     âĢ
    -0.72
     prior
    -0.72
    ãĢ
    -0.72
    depending
    -0.71
    âĢİ
    -0.71
    ï¸ı
    -0.70
     during
    -0.70
    -0.69
    ãĤ¦
    -0.68
    POSITIVE LOGITS
     again
    0.79
     crap
    0.78
     everybody
    0.78
     crappy
    0.72
     blah
    0.72
     worthless
    0.71
    again
    0.70
     lousy
    0.69
     theirs
    0.69
     nobody
    0.69
    Activations Density 1.153%

    No Known Activations