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. 4-RES-JB
    6. 8875
    Prev
    Next
    INDEX
    Explanations

    instances of an action happening at a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    the word "once" and related concepts of singularity or repetition in actions

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

    No Comments

    Negative Logits
    NRS
    -0.72
    alf
    -0.71
     âĸº
    -0.68
    DIT
    -0.67
    hemat
    -0.67
    needs
    -0.66
    pace
    -0.66
    MSN
    -0.66
    onga
    -0.66
    LCS
    -0.65
    POSITIVE LOGITS
     again
    0.78
     Bucc
    0.75
     bitten
    0.72
     Upon
    0.70
    falls
    0.70
     glance
    0.68
     tasted
    0.67
     glimps
    0.65
     patron
    0.65
     sensed
    0.64
    Activations Density 0.023%

    No Known Activations