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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 14664
    Prev
    Next
    INDEX
    Explanations

    mentions or references related to disc golf

    oai_token-act-pair · gpt-3.5-turbo

    references to disc golf

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.70
    \<
    -0.69
    atory
    -0.67
     Holmes
    -0.66
    mberg
    -0.65
    terday
    -0.65
    ahime
    -0.63
    HCR
    -0.60
     impunity
    -0.59
    paces
    -0.59
    POSITIVE LOGITS
    erning
    1.21
    ourses
    1.20
    ontent
    1.03
    washer
    1.01
    ursive
    1.01
    ont
    1.00
    ussions
    0.98
    rim
    0.98
    ounter
    0.96
    ription
    0.96
    Activations Density 0.014%

    No Known Activations