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. 1-RES-JB
    6. 13611
    Prev
    Next
    INDEX
    Explanations

    references to weight classes in combat sports

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "welterweight" in combat sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CPC
    -0.77
    uyomi
    -0.75
     Scientist
    -0.74
    ulhu
    -0.66
     Nature
    -0.65
    displayText
    -0.64
    urai
    -0.64
     Gravity
    -0.64
     Pear
    -0.63
     Science
    -0.63
    POSITIVE LOGITS
     wel
    1.31
    nut
    1.02
    terness
    0.93
    tering
    0.89
     challeng
    0.87
    nuts
    0.84
    weights
    0.83
     unden
    0.83
    keye
    0.81
    sword
    0.75
    Activations Density 0.005%

    No Known Activations