© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and biochemical mechanisms, such as endothelial dysfunction, oxidative stress, and signal transduction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vascular health and dysfunction

    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
    ecided
    -0.85
    rals
    -0.83
    soDeliveryDate
    -0.81
    uggets
    -0.80
    é¾
    -0.80
    utor
    -0.79
    rists
    -0.76
     Brands
    -0.75
    ãĤ±
    -0.75
    poons
    -0.74
    POSITIVE LOGITS
     apopt
    1.72
     oxidative
    1.44
     inhibition
    1.30
     proliferation
    1.28
     induction
    1.24
     degradation
    1.24
     activation
    1.22
     differentiation
    1.21
     depletion
    1.18
     replication
    1.18
    Activations Density 0.188%

    No Known Activations