© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 10013
    Prev
    Next
    INDEX
    Explanations

    legal and political terms

    oai_token-act-pair · gpt-3.5-turbo

    references to governance and legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colour
    -0.69
     Reference
    -0.63
    ounce
    -0.61
    ishable
    -0.61
     Suppose
    -0.60
    ograph
    -0.57
    ibli
    -0.57
    Ear
    -0.57
     Discuss
    -0.57
    manac
    -0.57
    POSITIVE LOGITS
     succeeded
    1.17
     culminated
    1.11
    successfully
    1.06
     lately
    0.93
     resulted
    0.92
     successes
    0.92
     unsuccessfully
    0.90
     aided
    0.87
    failed
    0.86
     succeeds
    0.85
    Activations Density 0.825%

    No Known Activations