© 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. 8-RES-JB
    11. 19301
    Prev
    Next
    INDEX
    Explanations

    pairs of opposites or contrasts in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "differently" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    urance
    -0.77
     publication
    -0.75
    stay
    -0.69
     subsequ
    -0.69
    raltar
    -0.66
     passage
    -0.65
     comprehension
    -0.63
     supremacy
    -0.62
     Mouth
    -0.62
    ————————
    -0.61
    POSITIVE LOGITS
     situated
    1.04
     disposed
    1.02
     inclined
    1.00
     tuned
    0.92
     configured
    0.90
    selected
    0.89
     suited
    0.87
     impacted
    0.87
    graded
    0.86
     affected
    0.84
    Activations Density 0.044%

    No Known Activations