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. 10125
    Prev
    Next
    INDEX
    Explanations

    references to the word "Pompe" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly related to the name "Pompeo" and the word "Rome."

    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
    Fla
    -0.77
    IFT
    -0.71
    INT
    -0.68
    ãĤ·ãĥ£
    -0.68
    ernels
    -0.67
    bucks
    -0.67
    patrick
    -0.67
    waukee
    -0.67
    Balt
    -0.66
    ðĿ
    -0.66
    POSITIVE LOGITS
    phrine
    0.88
    xual
    0.86
    alties
    0.76
    ethy
    0.76
    ously
    0.75
     Tone
    0.75
    lihood
    0.75
    erous
    0.75
    aux
    0.73
    olithic
    0.72
    Activations Density 0.025%

    No Known Activations