© 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. 11-RES-JB
    11. 13134
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and physiology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological, physiological, and genetic aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iva
    -0.80
    edited
    -0.75
    nered
    -0.75
    cius
    -0.75
    igun
    -0.74
    AH
    -0.73
    ocrates
    -0.72
    ibles
    -0.72
    IUM
    -0.71
    tower
    -0.71
    POSITIVE LOGITS
     significance
    1.20
     correlates
    1.14
     abnormalities
    1.09
     similarities
    1.09
     makeup
    1.05
     differences
    1.04
     basis
    1.04
     anomalies
    1.03
     alterations
    1.03
     consequences
    1.02
    Activations Density 0.117%

    No Known Activations