© 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. 13582
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to governmental processes and accountability

    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
    Interstitial
    -0.90
    å°Ĩ
    -0.86
    ierre
    -0.71
    iovascular
    -0.71
    riber
    -0.71
    uties
    -0.71
    xual
    -0.70
    erald
    -0.70
    anian
    -0.70
     teasp
    -0.69
    POSITIVE LOGITS
     its
    1.01
     itself
    0.90
     NGOs
    0.83
     Morocco
    0.83
     Albania
    0.82
     Islamabad
    0.82
     PBS
    0.79
     Bangladesh
    0.79
     Bahrain
    0.78
     Cuba
    0.78
    Activations Density 0.419%

    No Known Activations