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. 13794
    Prev
    Next
    INDEX
    Explanations

    the name "Kenyatta"

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific individual or character

    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
    naire
    -0.99
    atures
    -0.92
    aire
    -0.90
    ories
    -0.83
    aries
    -0.80
    naires
    -0.74
    lings
    -0.71
    WER
    -0.70
    ational
    -0.70
    ary
    -0.68
    POSITIVE LOGITS
    atta
    1.28
    hedral
    1.10
    velength
    0.93
    ascus
    0.89
     Lumpur
    0.88
    veyard
    0.86
    abba
    0.83
    uthor
    0.83
    cffff
    0.81
     fined
    0.77
    Activations Density 0.019%

    No Known Activations