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. 8-RES-JB
    6. 4840
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort or dedication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to effort and time investment

    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
     helicop
    -0.78
    ittle
    -0.74
     agre
    -0.73
    \\\\\\\\
    -0.72
    idden
    -0.72
    vertisement
    -0.70
     livest
    -0.69
    etheless
    -0.69
     convol
    -0.68
    reditary
    -0.67
    POSITIVE LOGITS
     oneself
    0.64
     to
    0.64
    ANA
    0.64
    ï¸ı
    0.61
     him
    0.61
     entails
    0.60
     for
    0.59
    .''.
    0.59
    GW
    0.58
     advantage
    0.58
    Activations Density 0.042%

    No Known Activations