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. 12385
    Prev
    Next
    INDEX
    Explanations

    references to rankings or standings within sports leagues

    oai_token-act-pair · gpt-3.5-turbo

    references to a competitive sports league

    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
    EStream
    -0.86
    imura
    -0.69
    anamo
    -0.69
    etsk
    -0.67
    «
    -0.67
     Virtue
    -0.66
    ihara
    -0.66
     Liberties
    -0.65
     Rider
    -0.65
    imaru
    -0.65
    POSITIVE LOGITS
     standings
    0.77
    average
    0.75
    wide
    0.75
     playoffs
    0.73
     commissioner
    0.73
     chang
    0.73
     Scouting
    0.72
    oster
    0.72
     championships
    0.71
     lockout
    0.68
    Activations Density 0.019%

    No Known Activations