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. 3-RES-JB
    6. 14188
    Prev
    Next
    INDEX
    Explanations

    the name "Rodgers" mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely a sports figure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.88
    uates
    -0.73
    izations
    -0.72
    uated
    -0.72
     horizon
    -0.66
    uating
    -0.64
     Liberties
    -0.62
     downside
    -0.62
    ting
    -0.62
     coordination
    -0.61
    POSITIVE LOGITS
     Rodgers
    1.04
    mith
    0.80
    manship
    0.80
    sey
    0.79
     Yards
    0.77
    etta
    0.76
    adier
    0.76
    cliffe
    0.75
    gers
    0.75
    bey
    0.74
    Activations Density 0.005%

    No Known Activations