© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6726
    Prev
    Next
    INDEX
    Explanations

    references to the word "lucky" within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "luck" or "fortunate"

    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
    ainer
    -0.92
    ational
    -0.78
    atter
    -0.75
    helle
    -0.74
    heny
    -0.71
    lain
    -0.71
    ciplinary
    -0.71
    PLIED
    -0.70
    ansion
    -0.70
    contained
    -0.70
    POSITIVE LOGITS
     lucky
    1.01
     charms
    0.84
     charm
    0.80
     souls
    0.74
     Lucky
    0.74
     Charm
    0.73
     unlucky
    0.70
     bastard
    0.69
    balls
    0.68
     luck
    0.68
    Activations Density 0.013%

    No Known Activations