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. 0-RES-JB
    6. 21321
    Prev
    Next
    INDEX
    Explanations

    numbers representing quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to the number forty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    auer
    -0.85
    inventoryQuantity
    -0.74
    çķ
    -0.66
    hiro
    -0.66
    ãĥ
    -0.63
    vere
    -0.63
     agre
    -0.62
    isa
    -0.62
     Nanto
    -0.61
    lee
    -0.61
    POSITIVE LOGITS
     40
    2.89
     41
    2.15
     35
    2.14
     50
    2.13
     45
    2.09
     70
    2.09
     60
    2.08
     30
    2.07
     42
    2.03
     80
    2.02
    Activations Density 0.030%

    No Known Activations