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. 11-RES-JB
    6. 8190
    Prev
    Next
    INDEX
    Explanations

    mentions of various books

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the phrase "Book of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isu
    -0.88
     bandwagon
    -0.70
    AMI
    -0.66
    gpu
    -0.65
    bent
    -0.64
    ously
    -0.61
    flo
    -0.61
    ryce
    -0.60
     outdoors
    -0.58
    nexus
    -0.56
    POSITIVE LOGITS
     Mormon
    1.00
     Contents
    0.95
     Revelation
    0.91
     Spells
    0.90
     Lists
    0.87
     Rights
    0.86
     Revelations
    0.85
     Records
    0.81
     Songs
    0.78
     Esther
    0.78
    Activations Density 0.040%

    No Known Activations