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. 20921
    Prev
    Next
    INDEX
    Explanations

    phrases related to concepts of continuation, extension, or replacement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections

    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
    Fight
    -0.71
    --------
    -0.64
    ussen
    -0.64
     buildup
    -0.64
    RD
    -0.63
     stakes
    -0.62
    $$$$
    -0.61
    metics
    -0.61
    oji
    -0.60
    fw
    -0.60
    POSITIVE LOGITS
     sorts
    0.78
     Pale
    0.69
    shoot
    0.67
     happ
    0.65
     defunct
    0.63
     existing
    0.63
     seasonal
    0.62
    ibrary
    0.62
     Eucl
    0.62
     feudal
    0.61
    Activations Density 0.244%

    No Known Activations