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. 7-RES-JB
    6. 5672
    Prev
    Next
    INDEX
    Explanations

    emotional or intensifying expressions such as exclamations

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory expressions and strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erness
    -0.79
    ascript
    -0.78
    ilater
    -0.74
    respective
    -0.73
    abetic
    -0.72
    ridor
    -0.69
    emaker
    -0.69
    udeb
    -0.68
    osuke
    -0.68
    iatric
    -0.67
    POSITIVE LOGITS
     Oops
    0.88
     Didn
    0.83
     huh
    0.83
     Wow
    0.82
     Wrong
    0.78
     Looks
    0.77
    Wr
    0.75
     Exactly
    0.75
     Congratulations
    0.74
     Stro
    0.73
    Activations Density 0.158%

    No Known Activations