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. 7-RES-JB
    6. 21050
    Prev
    Next
    INDEX
    Explanations

    tags or metadata

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.85
     citiz
    -0.80
     submar
    -0.76
    hement
    -0.76
     slashing
    -0.68
     Burgess
    -0.66
    orum
    -0.66
     volunte
    -0.66
     neighb
    -0.66
     ranc
    -0.65
    POSITIVE LOGITS
    CHAPTER
    0.98
    Beta
    0.95
    âĪ
    0.92
    Privacy
    0.91
    âĻ¥
    0.91
    Introduction
    0.91
    Author
    0.89
    Trivia
    0.88
    Version
    0.87
    MAL
    0.87
    Activations Density 0.078%

    No Known Activations