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. 3-RES-JB
    6. 2511
    Prev
    Next
    INDEX
    Explanations

    words related to uproar, chaos, and controversy

    oai_token-act-pair · gpt-3.5-turbo

    words related to rabble-rousing or inflammatory rhetoric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tsukuyomi
    -0.79
     Martian
    -0.76
     Reaper
    -0.71
     Andromeda
    -0.70
     Pebble
    -0.69
     Neptune
    -0.67
     Ceres
    -0.66
     Izan
    -0.66
     Ange
    -0.65
     Hercules
    -0.65
    POSITIVE LOGITS
     rab
    1.14
    ble
    0.96
    ozo
    0.95
    ody
    0.90
    iotics
    0.89
    hov
    0.82
    tags
    0.81
    iot
    0.81
    anus
    0.78
    esses
    0.78
    Activations Density 0.008%

    No Known Activations