Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 15171
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to performance outcomes in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.91
    abulary
    -0.79
    ibilities
    -0.76
    unity
    -0.74
    dayName
    -0.74
    ritical
    -0.73
    vernment
    -0.73
    orks
    -0.71
    obs
    -0.71
    hee
    -0.71
    POSITIVE LOGITS
     runner
    0.99
     tied
    0.98
     fourth
    0.89
     atop
    0.86
     fifth
    0.86
     ninth
    0.86
     second
    0.86
     sixth
    0.85
     seventh
    0.85
     eighth
    0.85
    Activations Density 0.060%

    No Known Activations