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. 0-RES-JB
    6. 14037
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix '-ially'

    oai_token-act-pair · gpt-3.5-turbo

    words ending with the suffix 'ially' or 'inx'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.78
    cloth
    -0.67
    MON
    -0.65
    main
    -0.64
     litter
    -0.62
    TEXT
    -0.62
    ste
    -0.62
    brand
    -0.61
     ster
    -0.60
     Stout
    -0.60
    POSITIVE LOGITS
    ially
    3.29
    iary
    1.78
    inx
    1.64
    ocating
    1.63
    iaries
    1.45
    iably
    1.42
    icably
    1.42
    ials
    1.37
    ial
    1.37
    aneously
    1.36
    Activations Density 0.025%

    No Known Activations