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. 16593
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Hol" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or name that starts with "Hol."

    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
    EED
    -0.73
    REE
    -0.69
    URI
    -0.68
    ITAL
    -0.64
    aeda
    -0.63
    Pool
    -0.63
    çͰ
    -0.62
     unauthorized
    -0.61
     Lowell
    -0.60
    kick
    -0.59
    POSITIVE LOGITS
    ocaust
    1.41
    iday
    1.37
    idays
    1.35
    ocene
    1.22
    oho
    1.03
    inar
    1.01
    mes
    1.00
    stery
    1.00
    isky
    0.97
    sters
    0.95
    Activations Density 0.029%

    No Known Activations