© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 4412
    Prev
    Next
    INDEX
    Explanations

    mentions of extremist or terrorist activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sadd
    -0.65
     Hath
    -0.65
     behold
    -0.64
     Labrador
    -0.61
     sober
    -0.57
    Ku
    -0.57
     congratulations
    -0.56
     shores
    -0.56
     ashore
    -0.55
     luck
    -0.54
    POSITIVE LOGITS
    lins
    1.18
    antle
    1.15
    acy
    1.11
    atorium
    1.07
    phasis
    1.07
    acists
    1.06
    nant
    1.02
    acist
    1.00
    phas
    0.98
    ascus
    0.91
    Activations Density 0.030%

    No Known Activations