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. 2439
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceptional or unparalleled events

    oai_token-act-pair · gpt-3.5-turbo
    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
    belt
    -0.76
    agra
    -0.76
    ather
    -0.74
    tops
    -0.72
    udder
    -0.69
    strings
    -0.69
    claimer
    -0.68
    uay
    -0.67
    guards
    -0.67
    ueller
    -0.65
    POSITIVE LOGITS
    ly
    0.97
    LY
    0.95
     proportions
    0.87
     unanim
    0.85
    itarian
    0.84
     amounts
    0.82
     occurrence
    0.82
     unprecedented
    0.81
    ITY
    0.79
     lows
    0.79
    Activations Density 0.038%

    No Known Activations