© 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. 6-RES-JB
    11. 24341
    Prev
    Next
    INDEX
    Explanations

    phrases related to being fortunate or lucky

    oai_token-act-pair · gpt-3.5-turbo

    expressions of good fortune or luck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    helle
    -0.76
    idine
    -0.72
    NF
    -0.70
    aul
    -0.69
    agher
    -0.68
    adish
    -0.68
    ravings
    -0.66
    arer
    -0.63
    ËĪ
    -0.62
    hemat
    -0.61
    POSITIVE LOGITS
     lucky
    0.99
     fortunate
    0.85
     charms
    0.83
     charm
    0.76
     absor
    0.71
    llor
    0.71
    Ń·
    0.70
     recipient
    0.69
    oise
    0.68
     enough
    0.68
    Activations Density 0.025%

    No Known Activations