© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    words related to hockey leagues and teams

    oai_token-act-pair · gpt-3.5-turbo

    references to hockey leagues and associated teams

    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
    cia
    -0.80
    zsche
    -0.78
    =-=-=-=-=-=-=-=-
    -0.76
    ophob
    -0.71
     Tao
    -0.71
    adiq
    -0.71
    math
    -0.70
    ãĥķ
    -0.69
    ometric
    -0.69
    olini
    -0.69
    POSITIVE LOGITS
     affiliate
    1.08
     playoffs
    1.08
     Playoffs
    1.05
     standings
    0.96
     Championship
    0.95
     Rookie
    0.94
     semifinals
    0.88
     Playoff
    0.88
     playoff
    0.87
     strugg
    0.85
    Activations Density 0.116%

    No Known Activations