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. 7569
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly athletes and public figures

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals related to sports and media

    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
    eness
    -0.96
    nian
    -0.86
    olar
    -0.86
    atche
    -0.85
    nov
    -0.83
    andal
    -0.79
    bol
    -0.77
    nit
    -0.76
    izophren
    -0.74
    ochond
    -0.74
    POSITIVE LOGITS
     Beckham
    0.71
    actory
    0.71
    iliary
    0.64
    minster
    0.62
     Messi
    0.60
     Foley
    0.60
    ranch
    0.60
     lure
    0.59
    catentry
    0.59
    Draft
    0.59
    Activations Density 0.054%

    No Known Activations