© 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. 8-RES-JB
    11. 13147
    Prev
    Next
    INDEX
    Explanations

    words related to technology and software updates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to video game versions and franchises

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Alert
    -0.68
    arious
    -0.68
    borgh
    -0.65
    proc
    -0.60
    Fla
    -0.60
    borough
    -0.60
    ãĤ¸
    -0.60
    ãĥĩãĤ£
    -0.59
    staking
    -0.58
     Tags
    -0.58
    POSITIVE LOGITS
     counterparts
    1.16
     counterpart
    1.15
     version
    1.05
     equivalents
    0.99
     versions
    0.98
     onwards
    0.92
     lacks
    0.83
     edition
    0.82
     fared
    0.81
     differs
    0.77
    Activations Density 0.652%

    No Known Activations