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. 4-RES-JB
    6. 13021
    Prev
    Next
    INDEX
    Explanations

    references to the Nintendo Wii gaming console

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nintendo Wii console

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

    No Comments

    Negative Logits
    onies
    -0.75
    inates
    -0.73
    */(
    -0.72
    cious
    -0.72
    uters
    -0.71
    ews
    -0.69
     choir
    -0.68
    oppers
    -0.68
    abwe
    -0.67
    pmwiki
    -0.67
    POSITIVE LOGITS
     Wii
    1.15
    Nintendo
    0.96
    Xbox
    0.94
    ©¶æ¥µ
    0.88
    Ware
    0.88
    Socket
    0.87
    Console
    0.85
     Fit
    0.84
    Wi
    0.83
    Gear
    0.83
    Activations Density 0.004%

    No Known Activations