© 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. 8-RES-JB
    11. 18617
    Prev
    Next
    INDEX
    Explanations

    words related to luck

    oai_token-act-pair · gpt-3.5-turbo

    references to luck or the concept of luck in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ceptor
    -0.74
    cept
    -0.73
    het
    -0.68
    deen
    -0.66
    pta
    -0.66
     Aram
    -0.66
    artisan
    -0.64
    bern
    -0.64
    ainers
    -0.64
    avez
    -0.64
    POSITIVE LOGITS
     charms
    1.02
    istically
    0.91
    iest
    0.91
     charm
    0.85
    ily
    0.82
    iness
    0.77
    igan
    0.77
     dice
    0.73
    bringer
    0.71
    ball
    0.70
    Activations Density 0.024%

    No Known Activations