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. 0-RES-JB
    6. 4450
    Prev
    Next
    INDEX
    Explanations

    references related to the sport of golf

    oai_token-act-pair · gpt-3.5-turbo

    mentions of disc golf

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actic
    -0.74
     Leviathan
    -0.72
    Luc
    -0.70
     Awoken
    -0.68
     Anon
    -0.67
     Innocent
    -0.66
    âĶĢâĶĢ
    -0.65
    asha
    -0.65
    Ïĥ
    -0.64
     Slave
    -0.63
    POSITIVE LOGITS
     golf
    3.84
     Golf
    3.05
     gol
    2.16
     tennis
    1.99
     bowling
    1.71
     Tennis
    1.60
     tee
    1.57
     baseball
    1.51
     skiing
    1.51
     basketball
    1.49
    Activations Density 0.022%

    No Known Activations