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. 15266
    Prev
    Next
    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation or phrases indicating the absence of something

    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
     pyramid
    -0.59
     warp
    -0.56
     Mobil
    -0.55
     Wilmington
    -0.55
     chained
    -0.54
     Lancaster
    -0.54
     Doodle
    -0.54
     cellphone
    -0.54
     logger
    -0.54
     Pyramid
    -0.54
    POSITIVE LOGITS
    ï¸ı
    1.04
    £
    0.94
    ¯¯
    0.88
    ¢
    0.86
    âĪ
    0.84
    âĶĢâĶĢâĶĢâĶĢ
    0.83
    âĸł
    0.82
    Pg
    0.82
    §
    0.81
    âĻ
    0.81
    Activations Density 0.321%

    No Known Activations