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. 8-RES-JB
    6. 21650
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of batteries and their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to batteries and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.77
    eker
    -0.73
    IFA
    -0.73
    ews
    -0.73
    orial
    -0.71
    querade
    -0.70
    iban
    -0.69
    ctors
    -0.69
    ei
    -0.67
    udo
    -0.66
    POSITIVE LOGITS
     charger
    1.02
     recharge
    0.99
     batteries
    0.99
     battery
    0.99
     compartment
    0.99
    Battery
    0.94
     strap
    0.93
     drain
    0.92
     storage
    0.92
     electrodes
    0.87
    Activations Density 0.033%

    No Known Activations