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. 3749
    Prev
    Next
    INDEX
    Explanations

    the concept of an action or event not occurring in the future

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "again."

    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
    ometric
    -0.63
     newcomers
    -0.63
     collective
    -0.61
     tents
    -0.58
     blackout
    -0.58
     throughput
    -0.56
     median
    -0.56
     privilege
    -0.55
    icipated
    -0.55
    OTS
    -0.55
    POSITIVE LOGITS
    eday
    0.82
    nir
    0.75
     someday
    0.75
    adays
    0.72
     :-)
    0.71
    leaf
    0.68
    fires
    0.68
    atile
    0.68
     ********************************
    0.67
    ingu
    0.67
    Activations Density 0.031%

    No Known Activations