© 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. 4-RES-JB
    11. 6257
    Prev
    Next
    INDEX
    Explanations

    words related to losing or defeat

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "lose" in different contexts

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

    No Comments

    Negative Logits
    Catalog
    -0.64
    orig
    -0.64
     Patri
    -0.63
    """
    -0.62
    cone
    -0.61
     semin
    -0.60
     Hale
    -0.59
     respondent
    -0.58
    Paul
    -0.58
     apolog
    -0.58
    POSITIVE LOGITS
    luster
    0.84
     Control
    0.81
     control
    0.77
    itaire
    0.75
    odder
    0.75
    ffen
    0.74
    veyard
    0.74
    ittens
    0.73
    enthal
    0.71
    æ©
    0.70
    Activations Density 0.048%

    No Known Activations