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. 1-RES-JB
    6. 19350
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    oai_token-act-pair · gpt-3.5-turbo

    references to database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.74
    irc
    -0.69
    tar
    -0.69
    antle
    -0.69
    trump
    -0.68
    ulla
    -0.67
    eryl
    -0.67
    ľ
    -0.67
    ŀ
    -0.66
     Joy
    -0.65
    POSITIVE LOGITS
     queries
    1.25
     query
    1.22
    Query
    0.99
     Query
    0.95
    query
    0.93
    naires
    0.86
     quer
    0.85
    naire
    0.82
    QL
    0.80
    greSQL
    0.71
    Activations Density 0.012%

    No Known Activations