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. 20143
    Prev
    Next
    INDEX
    Explanations

    specific mentions of clubs

    oai_token-act-pair · gpt-3.5-turbo

    references to various clubs, particularly those involved in advocacy or social groups

    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
     Marketable
    -0.84
    acious
    -0.74
    SourceFile
    -0.69
    ews
    -0.67
    é¾į
    -0.66
    inventoryQuantity
    -0.65
    older
    -0.65
    sbm
    -0.65
    aceous
    -0.64
    shown
    -0.63
    POSITIVE LOGITS
     Club
    1.15
    house
    0.94
    houses
    0.91
    bable
    0.90
     Clubs
    0.87
    bing
    0.84
    bies
    0.83
    feet
    0.78
    Club
    0.78
    Member
    0.76
    Activations Density 0.016%

    No Known Activations