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. 10-RES-JB
    6. 9617
    Prev
    Next
    INDEX
    Explanations

    instances of something happening for the first time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "for the first time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cart
    -0.58
    #$
    -0.58
    burn
    -0.58
    _.
    -0.56
     doom
    -0.56
    rend
    -0.55
    milo
    -0.55
    md
    -0.54
    bos
    -0.54
    killer
    -0.54
    POSITIVE LOGITS
     time
    1.42
    time
    1.01
     times
    0.90
     TIME
    0.88
     foreseeable
    0.87
     Time
    0.80
     decade
    0.80
     semester
    0.79
    TIME
    0.78
     instance
    0.78
    Activations Density 0.040%

    No Known Activations