© 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 EvalsExportsinterp-engineNEWAPI 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. 18788
    Prev
    Next
    INDEX
    Explanations

    instances where two entities are being compared or contrasted

    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
    ļéĨĴ
    -0.80
    renheit
    -0.79
    nect
    -0.76
    cise
    -0.72
    ocaust
    -0.72
    ugu
    -0.72
    uable
    -0.71
    Enlarge
    -0.71
    istle
    -0.69
    ylon
    -0.69
    POSITIVE LOGITS
     sides
    1.56
     sexes
    1.46
     parties
    1.31
     genders
    1.28
     halves
    1.20
     factions
    0.98
     versions
    0.98
     men
    0.95
     Houses
    0.94
     Parties
    0.92
    Activations Density 0.054%

    No Known Activations