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. 8-RES-JB
    6. 15243
    Prev
    Next
    INDEX
    Explanations

    names or references to a person named "Joshua."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Joshua."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolling
    -0.91
    chnology
    -0.91
    roleum
    -0.88
    rador
    -0.87
    mentation
    -0.83
    duct
    -0.83
    regation
    -0.81
    roller
    -0.80
    meal
    -0.79
    roxy
    -0.79
    POSITIVE LOGITS
     Hes
    0.92
     Joshua
    0.78
     Tree
    0.78
     Garland
    0.75
     Solomon
    0.69
     Isles
    0.68
     Moses
    0.68
     Figures
    0.68
     Cohen
    0.66
     Gunn
    0.65
    Activations Density 0.060%

    No Known Activations