© 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. 9-RES-JB
    11. 5546
    Prev
    Next
    INDEX
    Explanations

    phrases related to losing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lose" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.77
    furt
    -0.71
    sis
    -0.70
    agher
    -0.67
     Aires
    -0.66
     Janeiro
    -0.65
    Statement
    -0.63
    had
    -0.61
    iste
    -0.60
    NVIDIA
    -0.59
    POSITIVE LOGITS
     sight
    0.99
     virginity
    0.95
     limbs
    0.90
     credibility
    0.90
     patience
    0.86
     innocence
    0.82
     faith
    0.82
     momentum
    0.81
     consciousness
    0.81
     aversion
    0.81
    Activations Density 0.059%

    No Known Activations