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. 11-RES-JB
    6. 19668
    Prev
    Next
    INDEX
    Explanations

    phrases describing the cost, potential savings, and benefits of a product or service

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant emotional or life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torpedo
    -0.93
     Kissinger
    -0.86
     Tripoli
    -0.86
     Tel
    -0.86
     Liberty
    -0.84
     worm
    -0.84
     moss
    -0.80
     Libyan
    -0.80
     mushroom
    -0.79
     Essex
    -0.78
    POSITIVE LOGITS
    âĢ
    2.14
    âĸ
    1.63
    âĹ¼
    1.61
    Advertisements
    1.58
    âĢł
    1.53
    âĸł
    1.52
    âĹ
    1.51
    Anyway
    1.49
    âĿ
    1.49
    âľ
    1.47
    Activations Density 0.407%

    No Known Activations