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. 12168
    Prev
    Next
    INDEX
    Explanations

    words related to technology and gadgets

    oai_token-act-pair · gpt-3.5-turbo

    specific product names and technical terms

    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
    said
    -0.75
    #$#$
    -0.72
    still
    -0.70
    meric
    -0.68
    ffield
    -0.68
    thia
    -0.67
     seiz
    -0.67
     lawy
    -0.66
    amar
    -0.66
    shall
    -0.66
    POSITIVE LOGITS
    âĦ¢
    1.19
    ®
    1.09
     logo
    0.94
     moniker
    0.92
     Award
    0.92
     Trophy
    0.88
     Suite
    0.88
     Series
    0.86
     Awards
    0.85
     Foundation
    0.84
    Activations Density 0.415%

    No Known Activations