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. 4020
    Prev
    Next
    INDEX
    Explanations

    references to the name "McMahan" or variations of the name, such as "McMullin"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the last name "McM."

    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
    glers
    -1.15
    GER
    -0.80
    ger
    -0.79
    gers
    -0.79
    ging
    -0.78
    gered
    -0.77
    SHIP
    -0.76
    Interstitial
    -0.72
     gallery
    -0.70
    ãĥ³ãĤ¸
    -0.70
    POSITIVE LOGITS
    essage
    1.00
    ilitary
    0.93
    ansion
    0.89
    illian
    0.89
    ovember
    0.88
    argo
    0.87
    enn
    0.86
    ufact
    0.85
    asonic
    0.85
    ixed
    0.84
    Activations Density 0.013%

    No Known Activations