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. 5901
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to competition or conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to competitive situations, particularly in sports and elections

    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
    uct
    -0.71
    ä¸ī
    -0.69
    phia
    -0.68
    åº
    -0.67
    icone
    -0.66
    icity
    -0.65
    oxide
    -0.62
    trial
    -0.62
     Byzantine
    -0.62
    Ö¼
    -0.61
    POSITIVE LOGITS
     shoulders
    0.70
    quarters
    0.69
     heels
    0.64
    ggle
    0.61
    ratulations
    0.60
     collisions
    0.58
     nodd
    0.58
    quartered
    0.57
     antioxid
    0.57
     necks
    0.57
    Activations Density 0.101%

    No Known Activations