Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15298
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to batteries

    oai_token-act-pair · gpt-3.5-turbo

    specific details and metrics related to battery performance and characteristics

    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
     McCann
    -0.82
     Robertson
    -0.81
     puppet
    -0.80
    女
    -0.78
     Hispan
    -0.77
    =#
    -0.77
     pupp
    -0.76
     Osw
    -0.75
     chess
    -0.73
     Spiel
    -0.73
    POSITIVE LOGITS
     batteries
    1.88
     recharge
    1.74
     battery
    1.73
     lithium
    1.67
    Battery
    1.62
     charger
    1.62
     Battery
    1.51
     vape
    1.49
     Lith
    1.47
     coils
    1.46
    Activations Density 0.210%

    No Known Activations