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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 3807
    Prev
    Next
    INDEX
    Explanations

    names of authors or researchers, particularly in academic or scientific contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper names and references to authors in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aepernick
    -0.69
    inventoryQuantity
    -0.63
    ulhu
    -0.63
    eatured
    -0.59
     Thumbnails
    -0.59
     patriotic
    -0.58
    perty
    -0.58
     Anthem
    -0.58
    VERTISEMENT
    -0.57
     Eddie
    -0.57
    POSITIVE LOGITS
     et
    1.67
    oglu
    1.07
    meier
    1.00
     JM
    0.97
     JA
    0.95
    baum
    0.90
    ijk
    0.90
    aceae
    0.89
    ova
    0.89
    mann
    0.88
    Activations Density 0.197%

    No Known Activations