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. 21633
    Prev
    Next
    INDEX
    Explanations

    words related to gaming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming and the gaming industry

    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
    von
    -0.86
    drawn
    -0.75
     Debor
    -0.74
    geries
    -0.73
    orescent
    -0.68
    wered
    -0.67
    eous
    -0.67
    usions
    -0.67
    ioxide
    -0.66
    inators
    -0.66
    POSITIVE LOGITS
     consoles
    1.04
     prowess
    0.85
     gamers
    0.83
     peripher
    0.83
    manship
    0.80
     headsets
    0.80
     gaming
    0.80
    cube
    0.80
     enthusiasts
    0.79
    Stars
    0.78
    Activations Density 0.013%

    No Known Activations