© 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. 11-RES-JB
    11. 1534
    Prev
    Next
    INDEX
    Explanations

    biological or medical terms related to health and wellness

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of contracts and agreements

    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
    ationally
    -0.61
     rhet
    -0.60
    ãĤĵ
    -0.58
     "#
    -0.57
    among
    -0.57
     extensively
    -0.56
     plurality
    -0.56
    Ò
    -0.55
     exclusively
    -0.55
     colleg
    -0.55
    POSITIVE LOGITS
     survived
    1.04
     perished
    0.98
     vanished
    0.92
     survives
    0.90
     expires
    0.85
     disappeared
    0.84
     extinguished
    0.81
     surviving
    0.80
    pleted
    0.79
     destroyed
    0.78
    Activations Density 0.720%

    No Known Activations