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. 5716
    Prev
    Next
    INDEX
    Explanations

    text related to sports performance and achievements

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas and periods, which may indicate sentence structure or list formatting

    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
    yll
    -0.79
    sth
    -0.73
     <@
    -0.68
    erb
    -0.66
    reprene
    -0.65
    rite
    -0.64
    isure
    -0.63
    TeX
    -0.63
    riet
    -0.63
    irc
    -0.62
    POSITIVE LOGITS
     albeit
    0.91
     coached
    0.91
     rookie
    0.89
     teammate
    0.85
     Sammy
    0.85
     Rookie
    0.84
     undrafted
    0.84
     rookies
    0.84
    Team
    0.83
     athlet
    0.82
    Activations Density 0.426%

    No Known Activations