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. 8792
    Prev
    Next
    INDEX
    Explanations

    dates or numbers in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    indicators of social engagement and references to time or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Pros
    -0.61
    Russ
    -0.54
    CHA
    -0.50
    icka
    -0.47
    ²¾
    -0.47
    lam
    -0.46
    stead
    -0.46
    biz
    -0.46
     advoc
    -0.45
     rooting
    -0.45
    POSITIVE LOGITS
     expire
    0.65
     Mechdragon
    0.54
     Dragonbound
    0.51
     Lieutenant
    0.50
     expires
    0.49
     Baron
    0.48
     EDITION
    0.46
     Tags
    0.45
    };
    0.45
     declass
    0.45
    Activations Density 0.980%

    No Known Activations