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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20379
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Dominique."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "unique"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anger
    -0.75
    dfx
    -0.75
    itably
    -0.72
    TPPStreamerBot
    -0.72
    ough
    -0.70
    coming
    -0.70
    owment
    -0.70
    angers
    -0.68
    izoph
    -0.68
    mable
    -0.67
    POSITIVE LOGITS
    ique
    0.94
    eers
    0.90
    nil
    0.83
    eer
    0.79
     Royale
    0.78
     Vie
    0.74
     Franc
    0.68
    vre
    0.67
    urs
    0.67
    ira
    0.67
    Activations Density 0.028%

    No Known Activations