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. 441
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols that are not common in regular text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific special character or glyph

    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
    enegger
    -1.11
    gow
    -0.89
    ãģ®éŃĶ
    -0.87
    enburg
    -0.73
     Frey
    -0.70
     Sidd
    -0.67
    iator
    -0.66
    enberg
    -0.64
    iants
    -0.63
    ements
    -0.63
    POSITIVE LOGITS
    ³
    1.45
    ¹
    1.37
    µ
    1.33
    ¬
    1.32
    ¥
    1.32
    ¿
    1.31
    ¤
    1.27
    ¦
    1.26
    ¼
    1.25
    ¸
    1.24
    Activations Density 0.017%

    No Known Activations