© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 14306
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical values related to an increase or growth by a factor of two

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of doubling or increasing quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĬ
    -0.73
    ãĤĮ
    -0.70
    utic
    -0.69
    Interstitial
    -0.68
    в
    -0.67
    cheat
    -0.67
    esson
    -0.65
    ixtures
    -0.64
    RAW
    -0.64
    oga
    -0.64
    POSITIVE LOGITS
     digits
    0.80
     digit
    0.74
    peak
    0.69
     redundancy
    0.66
    cedes
    0.65
     exponentially
    0.62
    amount
    0.62
     consecut
    0.61
     hourly
    0.61
     tripled
    0.61
    Activations Density 0.032%

    No Known Activations