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. 7742
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mack" or "Mckenzie"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ck"

    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
     exha
    -0.95
    psons
    -0.89
     livest
    -0.87
     Palestin
    -0.81
     tremend
    -0.79
     occas
    -0.79
    accompan
    -0.79
     streng
    -0.79
    senal
    -0.78
    pora
    -0.76
    POSITIVE LOGITS
    erman
    1.07
    lace
    1.01
    enstein
    0.97
    ert
    0.97
    hoff
    0.96
    enger
    0.96
    oning
    0.95
    patrick
    0.95
    etts
    0.95
    ley
    0.94
    Activations Density 0.018%

    No Known Activations