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. 2-RES-JB
    6. 5060
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the name "Ema" or words with phonetic similarity to "Ema"

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to leadership and notable figures in Africa

    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
    ships
    -0.73
    sav
    -0.70
    drawn
    -0.65
    oward
    -0.63
     Avalon
    -0.63
     Breed
    -0.62
    =-=-=-=-
    -0.61
    selected
    -0.60
     Companion
    -0.60
    âĺħ
    -0.60
    POSITIVE LOGITS
    ema
    1.09
    utic
    0.96
    asar
    0.96
    utical
    0.94
    estro
    0.88
    isal
    0.87
    ption
    0.87
    ovic
    0.82
    pered
    0.81
    illance
    0.80
    Activations Density 0.009%

    No Known Activations