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. 16317
    Prev
    Next
    INDEX
    Explanations

    dates and numbers mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 11, especially in a historical or numerical context

    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
    PLIC
    -0.66
    è¯
    -0.65
    elo
    -0.65
     conduc
    -0.63
    meric
    -0.62
     conflic
    -0.61
    flows
    -0.60
    sers
    -0.60
    bler
    -0.58
    ãĥ¼ãĤ¯
    -0.58
    POSITIVE LOGITS
     11
    2.88
     12
    2.15
     13
    2.09
     14
    1.94
     10
    1.93
     eleven
    1.89
     9
    1.81
     17
    1.81
     21
    1.77
     16
    1.77
    Activations Density 0.034%

    No Known Activations