© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13642
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, particularly focusing on statistics and player comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performance or being excluded in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophile
    -0.63
     assemblies
    -0.62
    culosis
    -0.62
    sylv
    -0.60
    Policy
    -0.59
    alist
    -0.57
     fasc
    -0.56
     Scotia
    -0.56
    âĹ¼
    -0.56
     Gifts
    -0.54
    POSITIVE LOGITS
    stretched
    1.07
    played
    1.07
    scoring
    0.98
    paced
    0.95
    du
    0.91
    doing
    0.90
    matched
    0.90
    hitting
    0.88
    mus
    0.88
    framework
    0.87
    Activations Density 0.057%

    No Known Activations