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. 3-RES-JB
    6. 11738
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer software or systems

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to organizations or designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovych
    -0.69
    tip
    -0.61
     shine
    -0.60
     flo
    -0.58
     surprise
    -0.58
    recomm
    -0.56
    kaya
    -0.56
    kil
    -0.56
     latch
    -0.56
    schild
    -0.55
    POSITIVE LOGITS
    ulhu
    1.03
    pillar
    0.86
    arette
    0.85
    ornia
    0.78
    emporary
    0.78
    berus
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.77
    estial
    0.74
    CLE
    0.72
    orne
    0.71
    Activations Density 0.336%

    No Known Activations