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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 17598
    Prev
    Next
    INDEX
    Explanations

    the word 'luck'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "luck" and names associated with it

    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
     Rapids
    -0.62
     polyg
    -0.61
     Belg
    -0.61
     readable
    -0.60
     pipelines
    -0.60
     Kuwait
    -0.60
     locom
    -0.59
    ãĥ£
    -0.59
     neoc
    -0.59
     boiler
    -0.58
    POSITIVE LOGITS
    luck
    1.57
    DragonMagazine
    0.93
    theless
    0.91
    nir
    0.88
    ily
    0.88
    combe
    0.88
    wcs
    0.80
    Downloadha
    0.80
    unity
    0.78
    emon
    0.78
    Activations Density 0.008%

    No Known Activations