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. 8719
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or figures

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the number 38 in various contexts

    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
     rall
    -0.67
    staking
    -0.66
    trl
    -0.66
    ota
    -0.65
    thumbnails
    -0.64
     conduc
    -0.62
     perspect
    -0.61
    auer
    -0.60
    trap
    -0.60
    essors
    -0.59
    POSITIVE LOGITS
     38
    2.77
     39
    2.70
     37
    2.54
     36
    2.45
     34
    2.26
     41
    2.23
     35
    2.18
     33
    2.13
     42
    2.11
     43
    2.05
    Activations Density 0.051%

    No Known Activations