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. 10-RES-JB
    6. 13157
    Prev
    Next
    INDEX
    Explanations

    text formatting symbols

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing opinions or subjective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torpedo
    -0.99
     mushroom
    -0.85
     fermented
    -0.85
     loft
    -0.83
     sausage
    -0.81
     ego
    -0.80
     darts
    -0.79
     cheese
    -0.79
     sucker
    -0.78
     iron
    -0.78
    POSITIVE LOGITS
    âĢ
    2.31
    âĸł
    1.45
     âĢ
    1.37
    ________________________________
    1.33
    âľ
    1.31
    ãĢ
    1.28
    Comment
    1.26
    >>>
    1.26
    âĢł
    1.26
    âĺ
    1.24
    Activations Density 0.267%

    No Known Activations