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. 7-RES-JB
    6. 20359
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts, disputes, and negotiations involving various parties

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disputes or negotiations involving the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icter
    -0.75
    cks
    -0.74
     redistributed
    -0.71
    nosis
    -0.70
    burst
    -0.69
     largeDownload
    -0.69
    orah
    -0.69
    tracks
    -0.68
    enko
    -0.68
    clips
    -0.67
    POSITIVE LOGITS
     regard
    1.23
     regards
    1.17
    stood
    0.98
     respect
    0.92
     impunity
    0.91
     fellow
    0.85
    draw
    0.85
     creditors
    0.83
     superiors
    0.80
     coworkers
    0.79
    Activations Density 0.147%

    No Known Activations