© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    numbers written as digits with 3 and 8 in succession

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "3D" or related terms in technological contexts

    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
    staking
    -0.81
    esville
    -0.67
    sym
    -0.67
    rolet
    -0.61
    knife
    -0.59
    FontSize
    -0.58
    forth
    -0.54
     swearing
    -0.54
    itaire
    -0.54
    successfully
    -0.54
    POSITIVE LOGITS
    rd
    2.17
    RD
    1.26
    DS
    1.04
    dfx
    1.02
    peat
    0.97
    PO
    0.88
    ds
    0.84
     quarters
    0.84
    Aren
    0.82
    DES
    0.82
    Activations Density 0.110%

    No Known Activations