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. 16309
    Prev
    Next
    INDEX
    Explanations

    statistics related to appearances and performances in games

    oai_token-act-pair · gpt-3.5-turbo

    terms related to player statistics and participation in games

    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
    sonian
    -0.78
    resources
    -0.72
    wikipedia
    -0.70
    arde
    -0.70
    react
    -0.69
    rison
    -0.64
    erity
    -0.64
    aily
    -0.61
    ksh
    -0.61
    rified
    -0.61
    POSITIVE LOGITS
     Played
    0.99
     played
    0.91
     spanning
    0.90
     Ago
    0.84
     consecut
    0.80
     apiece
    0.79
     ago
    0.77
     logged
    0.76
     (.
    0.76
     worldwide
    0.74
    Activations Density 0.103%

    No Known Activations