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. 1-RES-JB
    6. 1304
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of batteries and their usage in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to batteries, particularly in the context of their usage and importance in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.83
    lihood
    -0.75
    Wilson
    -0.75
    Relations
    -0.74
    published
    -0.74
    ctors
    -0.73
     Foley
    -0.73
    American
    -0.72
    orial
    -0.71
    κ
    -0.69
    POSITIVE LOGITS
     batteries
    1.31
     battery
    1.09
     recharge
    0.99
     powering
    0.97
     charger
    0.97
    attery
    0.93
     electrodes
    0.92
     Battery
    0.91
     charg
    0.86
     enthusi
    0.86
    Activations Density 0.007%

    No Known Activations