Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2845
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those of individuals

    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
     Hurricanes
    -0.79
    sburgh
    -0.79
    DCS
    -0.77
     Dhabi
    -0.70
     Ruins
    -0.67
     Samoa
    -0.66
    Region
    -0.65
     Newfoundland
    -0.64
     Provincial
    -0.64
     Crimean
    -0.64
    POSITIVE LOGITS
    eman
    0.74
    cker
    0.72
    zinski
    0.72
    kowski
    0.69
    zynski
    0.68
    fill
    0.68
    agher
    0.67
    aney
    0.67
    ovich
    0.67
    etti
    0.67
    Activations Density 0.159%

    No Known Activations