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. 16081
    Prev
    Next
    INDEX
    Explanations

    references to sports games where a tie occurred

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive outcomes, particularly tying scores or standings in sports contexts

    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
    âĵĺ
    -0.79
    resources
    -0.79
    isma
    -0.75
    rians
    -0.74
    illing
    -0.73
    zos
    -0.71
    xit
    -0.68
     heterogeneity
    -0.68
    mining
    -0.65
    microsoft
    -0.65
    POSITIVE LOGITS
     streak
    0.87
     championship
    0.83
     Dwight
    0.82
     teammate
    0.81
     MVP
    0.80
     semifinals
    0.79
     opponents
    0.78
     playoff
    0.77
     unbeaten
    0.75
     opponent
    0.75
    Activations Density 0.105%

    No Known Activations