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. 19964
    Prev
    Next
    INDEX
    Explanations

    words related to professional relationships or collaborations

    oai_token-act-pair · gpt-3.5-turbo

    references to collaborative relationships and teamwork

    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
    cer
    -0.70
    ocker
    -0.62
    IFF
    -0.61
    erer
    -0.60
    icter
    -0.57
    Woman
    -0.57
    Chain
    -0.57
    earing
    -0.57
    ItemImage
    -0.57
    spir
    -0.56
    POSITIVE LOGITS
    hip
    1.04
    hips
    1.00
     abroad
    0.83
    peak
    0.81
    '
    0.79
     across
    0.76
    mates
    0.74
    ervative
    0.73
    heet
    0.72
     whom
    0.70
    Activations Density 0.117%

    No Known Activations