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. 8-RES-JB
    6. 20631
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to an individual named "Ay"

    oai_token-act-pair · gpt-3.5-turbo

    references to the title or name "Ayatollah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.89
    DragonMagazine
    -0.71
    éĹĺ
    -0.68
     Gutenberg
    -0.65
     Eclipse
    -0.64
    dfx
    -0.63
    istics
    -0.62
     Gemini
    -0.62
    pmwiki
    -0.62
    DERR
    -0.62
    POSITIVE LOGITS
    ahu
    1.23
    bara
    1.04
    meric
    1.00
    umi
    0.91
    atana
    0.90
    yy
    0.86
    alon
    0.86
    aya
    0.86
    rika
    0.85
    annis
    0.83
    Activations Density 0.034%

    No Known Activations