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. 4-RES-JB
    6. 23832
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Johan Bhagwat Mohan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Gohan" and "Ammu."

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

    No Comments

    Negative Logits
    ©¶æ
    -0.81
    impro
    -0.72
    urgical
    -0.71
    etitive
    -0.70
     WATCHED
    -0.68
    acement
    -0.68
     stakes
    -0.67
     periodic
    -0.67
    taboola
    -0.66
     newsletters
    -0.66
    POSITIVE LOGITS
    ohan
    0.89
    ansen
    0.88
    ovan
    0.87
    anye
    0.83
     Lauder
    0.83
     Marino
    0.81
    igan
    0.80
     Yor
    0.80
     Grimes
    0.78
     Singh
    0.78
    Activations Density 0.006%

    No Known Activations