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. 19986
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Albert" followed by another name or title, especially in a list or description of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Albert."

    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
    BOOK
    -0.87
    elcome
    -0.80
    pter
    -0.79
    mble
    -0.77
    ãĥ¯
    -0.74
    efully
    -0.74
    ned
    -0.72
    ning
    -0.72
    llular
    -0.71
    igation
    -0.70
    POSITIVE LOGITS
     Einstein
    1.01
     Calder
    0.83
     Pu
    0.74
    anus
    0.74
     Albert
    0.73
    inates
    0.71
     Hammond
    0.71
    stown
    0.67
     Schwe
    0.67
     Nob
    0.66
    Activations Density 0.007%

    No Known Activations