© 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. 18869
    Prev
    Next
    INDEX
    Explanations

    studies or research findings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Leilan
    -0.74
     amen
    -0.62
    react
    -0.62
    tsy
    -0.61
    usercontent
    -0.59
     Reaction
    -0.59
     Horus
    -0.59
    gencies
    -0.56
    ocratic
    -0.56
    apest
    -0.55
    POSITIVE LOGITS
     conducted
    1.02
     commissioned
    1.00
     published
    0.94
     suggests
    0.93
     spearheaded
    0.90
     authored
    0.90
     titled
    0.89
     examining
    0.86
     analyzing
    0.86
     undertaken
    0.85
    Activations Density 0.129%

    No Known Activations