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. 1-RES-JB
    6. 17419
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific entity or concept, possibly involving customs or religious practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "cel" or "Celest" and other associated variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.89
    shapeshifter
    -0.73
     Skydragon
    -0.69
    fact
    -0.68
    é¾įå¥ij士
    -0.66
    */(
    -0.65
    enegger
    -0.65
    hift
    -0.63
     EDITION
    -0.61
    [_
    -0.60
    POSITIVE LOGITS
    erity
    1.06
    antry
    0.95
     Cel
    0.95
    agos
    0.91
    estine
    0.90
     cel
    0.88
    wyn
    0.81
    atonin
    0.80
    anguage
    0.79
    mont
    0.78
    Activations Density 0.004%

    No Known Activations