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. 20013
    Prev
    Next
    INDEX
    Explanations

    names or partial names that contain "rie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly names and their associations

    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
    agnetic
    -0.87
    idious
    -0.86
    iop
    -0.81
    iary
    -0.81
    ially
    -0.78
    ailand
    -0.71
    agons
    -0.70
    tnc
    -0.70
    ial
    -0.70
    paio
    -0.68
    POSITIVE LOGITS
    vre
    1.03
    lect
    0.92
    ppa
    0.88
    vers
    0.87
    ger
    0.86
    zon
    0.85
    ves
    0.84
    ber
    0.84
    zo
    0.83
    rie
    0.82
    Activations Density 0.063%

    No Known Activations