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. 1-RES-JB
    6. 12634
    Prev
    Next
    INDEX
    Explanations

    instances of the word "during"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "during"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.81
    raid
    -0.76
    eri
    -0.74
    hou
    -0.73
    forward
    -0.72
    rail
    -0.69
    hazard
    -0.68
    ould
    -0.68
    hack
    -0.67
    van
    -0.66
    POSITIVE LOGITS
     periods
    0.80
     newsp
    0.80
     veter
    0.74
     livest
    0.74
     wartime
    0.74
     spotting
    0.73
     renovations
    0.73
     halftime
    0.71
     embry
    0.70
     times
    0.68
    Activations Density 0.033%

    No Known Activations