Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12512
    Prev
    Next
    INDEX
    Explanations

    phrases related to luck or fortunate circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to being "lucky" or fortunate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atter
    -0.70
     CTR
    -0.65
    helle
    -0.64
    models
    -0.63
    head
    -0.62
     leveled
    -0.62
    ravings
    -0.62
    heny
    -0.62
    ake
    -0.60
    ciplinary
    -0.60
    POSITIVE LOGITS
     lucky
    1.15
     fortunate
    0.99
     charms
    0.78
     unlucky
    0.75
     absor
    0.72
     unsuspecting
    0.70
    udeau
    0.69
     luck
    0.69
    bably
    0.68
    reys
    0.67
    Activations Density 0.006%

    No Known Activations