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. 8-RES-JB
    6. 1662
    Prev
    Next
    INDEX
    Explanations

    dual words with a common prefix, specifically a prefix accompanied by a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving exaggerated or extreme characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barron
    -0.79
     Norton
    -0.72
     Meadows
    -0.71
     Cox
    -0.68
     Burr
    -0.65
     Ples
    -0.65
     Eternity
    -0.64
     Roberts
    -0.64
     whence
    -0.64
     Borders
    -0.64
    POSITIVE LOGITS
    competitive
    1.23
    sized
    1.22
    optim
    1.21
    powered
    1.17
    popular
    1.16
    exclusive
    1.15
    expensive
    1.15
    compl
    1.14
    skilled
    1.12
    complex
    1.10
    Activations Density 0.032%

    No Known Activations