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. 22008
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy conservation and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gradual processes and timelines

    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
     appell
    -0.71
    National
    -0.69
     publicly
    -0.65
     Kahn
    -0.65
     Luxem
    -0.65
     Jur
    -0.65
     openly
    -0.65
    ylum
    -0.63
     representatives
    -0.62
    Government
    -0.62
    POSITIVE LOGITS
     cooldown
    1.01
     cpu
    1.00
     reload
    0.94
     humidity
    0.91
     drying
    0.90
     downtime
    0.89
     timer
    0.88
     refill
    0.87
     airflow
    0.84
     cleanup
    0.83
    Activations Density 0.903%

    No Known Activations