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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3812
    Prev
    Next
    INDEX
    Explanations

    words related to controllers, especially in the context of gaming

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming controllers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.87
    olit
    -0.74
    iary
    -0.73
    entimes
    -0.72
     Ruff
    -0.66
    onym
    -0.65
    ened
    -0.64
    inx
    -0.64
     Graham
    -0.63
     Fraz
    -0.63
    POSITIVE LOGITS
     controller
    0.79
    rollers
    0.75
    Deploy
    0.74
    pad
    0.73
    controller
    0.73
    wright
    0.71
    washer
    0.71
    eers
    0.70
    SHIP
    0.70
    Focus
    0.70
    Activations Density 0.017%

    No Known Activations