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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 625
    Prev
    Next
    INDEX
    Explanations

    names with a specific pattern: ending with "zan" or "ich"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names associated with individuals and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UCT
    -0.76
    ascript
    -0.76
    ivably
    -0.67
    aliation
    -0.65
    Db
    -0.64
     Thumbnails
    -0.63
     merc
    -0.62
     medic
    -0.62
    iencies
    -0.60
     fict
    -0.60
    POSITIVE LOGITS
    itsch
    1.09
    inski
    1.07
    owski
    1.05
    itzer
    1.00
    insky
    0.96
    owsky
    0.95
    ewski
    0.95
    nik
    0.92
    gaard
    0.91
    ovsky
    0.89
    Activations Density 0.221%

    No Known Activations