© 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. 2-RES-JB
    11. 17509
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, specifically those related to the spinal cord like "paraplegia."

    oai_token-act-pair · gpt-3.5-turbo

    references to drug paraphernalia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URI
    -0.67
     Delta
    -0.66
    20439
    -0.66
     Portuguese
    -0.62
    unct
    -0.62
     SAP
    -0.62
     Pixie
    -0.61
     Brazilian
    -0.61
    UTF
    -0.60
    Duration
    -0.60
    POSITIVE LOGITS
    alia
    1.17
    obyl
    1.14
    hern
    1.08
    igans
    0.98
    arus
    0.97
    igan
    0.94
    opol
    0.92
    atural
    0.91
    owitz
    0.87
    iah
    0.84
    Activations Density 0.010%

    No Known Activations