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. 17800
    Prev
    Next
    INDEX
    Explanations

    references to hockey-related terms

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

    terms related to various sports, particularly hockey

    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
     manoeuv
    -0.67
    igslist
    -0.66
     bud
    -0.64
     simul
    -0.62
     bicycl
    -0.62
     bicy
    -0.61
     ease
    -0.60
    EStream
    -0.59
     bis
    -0.57
     braking
    -0.57
    POSITIVE LOGITS
     Writers
    1.04
     League
    1.00
     Hall
    0.86
     Association
    0.77
     Gods
    0.76
    Hall
    0.75
     Reference
    0.75
     Focus
    0.74
    insula
    0.73
    Scene
    0.72
    Activations Density 0.024%

    No Known Activations