© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 678
    Prev
    Next
    INDEX
    Explanations

    terms related to success, achievement, and victory

    oai_token-act-pair · gpt-3.5-turbo

    instances of winning and success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to winning or victory.

    oai_token-act-pair · gpt-4oTriggered by @tatsatx
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annels
    -0.83
    anon
    -0.76
     vents
    -0.72
    houn
    -0.70
    rict
    -0.70
    pron
    -0.69
    Newsletter
    -0.68
    uga
    -0.67
    artments
    -0.67
    accessible
    -0.66
    POSITIVE LOGITS
     trophies
    1.06
     achieved
    0.96
     underdog
    0.95
     Defeat
    0.93
     victories
    0.93
     Winning
    0.93
     accol
    0.92
     achievements
    0.91
     Glory
    0.88
     Congratulations
    0.88
    Activations Density 0.687%

    No Known Activations