Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1036
    Prev
    Next
    INDEX
    Explanations

    references to physical forces and interactions between objects

    oai_token-act-pair · gpt-3.5-turbo

    references to various physical or metaphysical forces

    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
    mbuds
    -0.93
    apest
    -0.74
     Hop
    -0.72
    MAL
    -0.71
    ADRA
    -0.70
     iT
    -0.67
     Trident
    -0.66
    olitan
    -0.66
    nai
    -0.65
    yss
    -0.65
    POSITIVE LOGITS
     exerted
    1.07
     force
    0.94
     Awakens
    0.86
     maj
    0.85
     propelled
    0.73
     propel
    0.72
     forces
    0.72
     theorist
    0.72
     unbeliev
    0.71
     cooker
    0.70
    Activations Density 0.032%

    No Known Activations