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. 1491
    Prev
    Next
    INDEX
    Explanations

    sentences describing research studies or experiments

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that conclude with a punctuation mark

    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
     condol
    -0.82
     pardon
    -0.77
     defin
    -0.76
     pard
    -0.73
     clos
    -0.72
     renegoti
    -0.71
    rament
    -0.71
     toast
    -0.71
     certainly
    -0.71
     condolences
    -0.70
    POSITIVE LOGITS
     Each
    1.54
     They
    1.48
     Their
    1.46
     Participants
    1.46
     Researchers
    1.35
     Called
    1.35
     Using
    1.30
     Those
    1.28
     Among
    1.26
     Initially
    1.23
    Activations Density 0.360%

    No Known Activations