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. 4-RES-JB
    6. 7780
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming or code.<br>

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'C' in a variety of contexts

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

    No Comments

    Negative Logits
    Magikarp
    -0.75
    hof
    -0.74
    ãĥĦ
    -0.73
     Tinder
    -0.69
     Yamaha
    -0.69
     absor
    -0.68
    ItemTracker
    -0.67
     milit
    -0.63
     Wrestle
    -0.62
    EStream
    -0.62
    POSITIVE LOGITS
    overed
    1.15
    URRENT
    1.09
    olly
    1.09
    argo
    1.07
    ancel
    1.05
    isco
    1.04
    ursor
    1.03
    ollo
    1.03
    urses
    1.02
    rouch
    1.02
    Activations Density 0.048%

    No Known Activations