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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 23887
    Prev
    Next
    INDEX
    Explanations

    terms related to entrepreneurship, innovation, legislation, and regeneration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to innovation and legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.76
     Doctrine
    -0.75
    manship
    -0.74
     Divinity
    -0.70
     Dragonbound
    -0.70
     Penet
    -0.68
     ACTION
    -0.68
     Principle
    -0.68
     Grail
    -0.67
    WAYS
    -0.66
    POSITIVE LOGITS
    ating
    1.60
    ators
    1.54
    ated
    1.49
    ator
    1.43
    ational
    1.39
    ations
    1.33
    ates
    1.29
    atively
    1.28
    atable
    1.24
    ative
    1.17
    Activations Density 0.061%

    No Known Activations