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. 3-RES-JB
    6. 19827
    Prev
    Next
    INDEX
    Explanations

    expressions of pride or positivity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proudly" and similar expressions of pride or prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Annotations
    -0.77
    vae
    -0.75
     Sequence
    -0.72
    ergus
    -0.66
    ebin
    -0.65
    nesota
    -0.63
     Killer
    -0.61
    EMS
    -0.59
    ests
    -0.59
     Rapp
    -0.59
    POSITIVE LOGITS
     proudly
    0.89
     proclaim
    0.87
     displayed
    0.82
     proclaiming
    0.80
     boasted
    0.80
     proclaimed
    0.75
    ãĤ©
    0.74
     boasting
    0.73
     disguised
    0.71
    roud
    0.68
    Activations Density 0.008%

    No Known Activations