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. 15190
    Prev
    Next
    INDEX
    Explanations

    phrases related to ice hockey goalkeeping statistics, particularly save percentages and the number of saves made

    oai_token-act-pair · gpt-3.5-turbo

    references to saves in hockey statistics

    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
    Else
    -0.94
    yond
    -0.74
    enberg
    -0.72
    RY
    -0.72
    cale
    -0.71
    naire
    -0.67
    issance
    -0.63
    ounced
    -0.63
    hester
    -0.63
    orporated
    -0.63
    POSITIVE LOGITS
    éĹĺ
    0.87
     Cache
    0.74
     TOR
    0.73
     Marcos
    0.66
     Sanctuary
    0.66
     Save
    0.65
    orage
    0.64
    Save
    0.64
     Shelter
    0.63
     Deposit
    0.61
    Activations Density 0.018%

    No Known Activations