© 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. 12-RES-JB
    11. 2812
    Prev
    Next
    INDEX
    Explanations

    mentions of epidemiological information such as diseases, outbreaks, and medical conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of reported cases and incidents related to health and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ļéĨĴ
    -0.76
    IPS
    -0.73
     Altern
    -0.72
    vation
    -0.72
    ħĭ
    -0.71
    tainment
    -0.68
    NES
    -0.67
     Directions
    -0.66
     Conversation
    -0.65
    eln
    -0.64
    POSITIVE LOGITS
     involving
    1.31
     reported
    1.26
     occurring
    1.15
     documented
    1.13
     attributed
    1.08
     detected
    1.08
     recorded
    1.07
     investigated
    1.07
     linked
    1.05
     alleging
    1.03
    Activations Density 0.211%

    No Known Activations