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. 5524
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Kel" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns ending in "kel"

    oai_token-act-pair · gpt-3.5-turbo
    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
    LEASE
    -0.75
     Bucc
    -0.69
     Parables
    -0.68
     crowds
    -0.67
    Reply
    -0.64
    ILLE
    -0.64
     Debor
    -0.63
     Bay
    -0.59
    ño
    -0.59
     âĶľ
    -0.59
    POSITIVE LOGITS
    anguage
    1.08
    stein
    1.03
    iban
    1.00
    abor
    0.94
    ogy
    0.93
    bach
    0.89
    sen
    0.88
    mann
    0.88
    patrick
    0.87
    ophon
    0.86
    Activations Density 0.067%

    No Known Activations