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. 10414
    Prev
    Next
    INDEX
    Explanations

    information related to quantities of money, numbers, or specific units

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly in terms of yearly and daily measurements

    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
    NetMessage
    -0.69
     Hollow
    -0.68
    ayn
    -0.68
    bye
    -0.68
     Helm
    -0.67
     Winter
    -0.66
     Barr
    -0.65
    virt
    -0.64
     Oss
    -0.62
    wolves
    -0.62
    POSITIVE LOGITS
    oline
    0.82
    Downloadha
    0.81
    taboola
    0.79
     occupancy
    0.75
     averages
    0.72
     expenditure
    0.72
     capita
    0.66
     increments
    0.64
    occup
    0.63
     (%
    0.62
    Activations Density 0.070%

    No Known Activations