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. 1216
    Prev
    Next
    INDEX
    Explanations

    names or acronyms related to sporting organizations and events

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations related to sports organizations and events

    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
    veh
    -0.81
    rou
    -0.78
     Hof
    -0.69
    onen
    -0.68
    rosc
    -0.66
    var
    -0.64
     Hem
    -0.63
    ht
    -0.62
    fi
    -0.62
    hra
    -0.62
    POSITIVE LOGITS
     Classics
    0.88
    HY
    0.79
    IFIED
    0.75
    ODUCT
    0.73
    eers
    0.72
    ILLE
    0.72
    xual
    0.69
    DX
    0.68
    ICAN
    0.67
     Sorceress
    0.66
    Activations Density 0.103%

    No Known Activations