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. 6-RES-JB
    6. 15583
    Prev
    Next
    INDEX
    Explanations

    instances of numbers representing quantities of items or people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific quantities or counts, particularly related to deaths or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agame
    -0.80
     [&
    -0.73
    biology
    -0.69
     fert
    -0.66
     goodness
    -0.65
    Temperature
    -0.65
    needs
    -0.65
    Platform
    -0.64
    vention
    -0.63
    given
    -0.63
    POSITIVE LOGITS
    teen
    1.05
    teenth
    0.97
     unnamed
    0.95
     dozen
    0.95
     consecutive
    0.93
     successive
    0.92
     prominent
    0.89
     unidentified
    0.89
     eyewitness
    0.88
     months
    0.86
    Activations Density 0.214%

    No Known Activations