Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21038
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending with either "ull" or "ullin"

    oai_token-act-pair · gpt-3.5-turbo

    specific names or entities related to an individual named "Mull" or variations of that name

    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
    ãĢIJ
    -0.65
    BOOK
    -0.64
    nerg
    -0.63
    zig
    -0.61
    âĸ¬âĸ¬
    -0.61
    Charges
    -0.60
    ãĥ¥
    -0.60
     Quan
    -0.60
    merce
    -0.59
    Charge
    -0.59
    POSITIVE LOGITS
    sburg
    1.45
    iard
    1.11
    owship
    1.08
    aby
    1.07
    sburgh
    1.03
    inx
    1.03
    enic
    1.02
    abies
    0.98
    igans
    0.97
    abal
    0.96
    Activations Density 0.034%

    No Known Activations