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. 5476
    Prev
    Next
    INDEX
    Explanations

    legal and legislative terminology

    oai_token-act-pair · gpt-3.5-turbo

    titles or headings from documents

    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
     freel
    -0.83
     racer
    -0.76
     Thrones
    -0.75
     Frozen
    -0.75
     esports
    -0.75
     Toro
    -0.73
     champ
    -0.72
     mall
    -0.71
     stomp
    -0.71
     accelerator
    -0.68
    POSITIVE LOGITS
    Introduction
    1.31
    http
    1.28
    Dear
    1.28
    ================================================================
    1.21
    summary
    1.19
    ~~~~~~~~~~~~~~~~
    1.19
    Summary
    1.19
    Overview
    1.18
    ================================
    1.17
    Synopsis
    1.16
    Activations Density 0.442%

    No Known Activations