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. 8526
    Prev
    Next
    INDEX
    Explanations

    the name "Chen" or related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Chen."

    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
     critically
    -0.64
    regon
    -0.63
    ODUCT
    -0.61
    INT
    -0.61
     physically
    -0.60
     Buffy
    -0.60
    usting
    -0.60
     grading
    -0.60
    inals
    -0.60
    grading
    -0.59
    POSITIVE LOGITS
    chen
    1.48
    wald
    1.02
    emy
    0.97
     Awakens
    0.95
    nai
    0.94
    kov
    0.89
    pai
    0.86
    nis
    0.85
    nut
    0.84
    thal
    0.84
    Activations Density 0.008%

    No Known Activations