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. 10-RES-JB
    6. 22551
    Prev
    Next
    INDEX
    Explanations

    the name "Jonathan" with high activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jonathan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ials
    -0.76
    Ħ¢
    -0.75
    eatures
    -0.75
    shots
    -0.73
    atically
    -0.73
    spring
    -0.71
    ebin
    -0.71
    housing
    -0.71
    algia
    -0.70
    agall
    -0.69
    POSITIVE LOGITS
    athan
    0.88
     Pearce
    0.86
     Daniels
    0.80
     Swift
    0.78
     Edwards
    0.78
     Cape
    0.77
     Gru
    0.77
     Coul
    0.77
     Kushner
    0.75
     Bernstein
    0.74
    Activations Density 0.028%

    No Known Activations