Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 17739
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to physical sensations like heart rate changes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words associated with heart and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    idon
    -0.79
     Pixie
    -0.74
    detail
    -0.73
     Surveillance
    -0.73
    idem
    -0.71
    levard
    -0.70
     Aval
    -0.70
    VIEW
    -0.70
     Conce
    -0.70
    xual
    -0.69
    POSITIVE LOGITS
     throb
    1.18
     pounding
    1.04
     churn
    0.99
     racing
    0.98
     swell
    0.95
     pound
    0.95
     clen
    0.95
     ac
    0.95
     pumping
    0.94
     clenched
    0.92
    Activations Density 0.225%

    No Known Activations