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. 14913
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or entities with the title "Ts"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of references to the Tsunami

    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
    nesota
    -0.79
    naissance
    -0.78
     mileage
    -0.73
    ously
    -0.71
    heid
    -0.71
    SOURCE
    -0.70
    ãĥ¼ãĥĨ
    -0.69
    liness
    -0.69
    formance
    -0.68
    iously
    -0.68
    POSITIVE LOGITS
    arnaev
    1.07
    avorite
    1.02
    ouk
    0.96
    ug
    0.96
    izoph
    0.94
    omp
    0.94
    unin
    0.93
    arist
    0.86
    onic
    0.86
    ugi
    0.86
    Activations Density 0.008%

    No Known Activations