Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5825
    Prev
    Next
    INDEX
    Explanations

    instances where the word "once" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases using the word "once."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rug
    -0.75
    onga
    -0.72
    RIC
    -0.70
    ander
    -0.69
    oco
    -0.68
    enda
    -0.67
    oler
    -0.66
    aze
    -0.65
     âĸº
    -0.65
    roth
    -0.64
    POSITIVE LOGITS
     again
    0.92
     Upon
    0.80
     bitten
    0.78
    soever
    0.73
    handedly
    0.71
     mastered
    0.69
    terday
    0.69
     seated
    0.66
     upon
    0.65
     tasted
    0.65
    Activations Density 0.026%

    No Known Activations