© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 495
    Prev
    Next
    INDEX
    Explanations

    references to "Super Smash Bros," a video game series

    oai_token-act-pair · gpt-4-turbo

    references to the video game "Smash Bros."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Smash" game series and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vest
    -0.69
    urion
    -0.65
     deliberations
    -0.63
     foss
    -0.63
     administrations
    -0.63
     horns
    -0.61
     agon
    -0.61
     deliber
    -0.61
     Kling
    -0.60
    ciation
    -0.58
    POSITIVE LOGITS
    halla
    1.14
     Smash
    0.90
    words
    0.87
    adelphia
    0.83
     Bros
    0.83
    Flash
    0.80
     Mouth
    0.79
    lda
    0.78
     Showdown
    0.76
    Wiki
    0.75
    Activations Density 0.014%

    No Known Activations