© 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. 1-RES-JB
    11. 21464
    Prev
    Next
    INDEX
    Explanations

    mentions of luck or fortune

    oai_token-act-pair · gpt-3.5-turbo

    references to social inequality and the concept of being fortunate or less fortunate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    head
    -0.86
    heads
    -0.74
    ope
    -0.64
    alcohol
    -0.63
    ood
    -0.63
    dress
    -0.62
    bank
    -0.62
    gap
    -0.61
     CTR
    -0.61
    Drug
    -0.61
    POSITIVE LOGITS
     fortunate
    1.33
     lucky
    0.92
    udeau
    0.90
    ortunate
    0.90
     adolesc
    0.86
    uitous
    0.85
     circumstance
    0.83
    romeda
    0.81
    Ń·
    0.80
     honoured
    0.78
    Activations Density 0.008%

    No Known Activations