© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    medical terms and drug-related information

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

    phrases related to medical studies and their outcomes

    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
    vironment
    -0.83
    externalActionCode
    -0.74
     Billion
    -0.73
    soType
    -0.71
    billion
    -0.69
    uts
    -0.69
    orean
    -0.69
    quartered
    -0.68
    ãģĨ
    -0.67
    pees
    -0.65
    POSITIVE LOGITS
     remission
    1.60
     relapse
    1.44
     sympt
    1.19
     symptom
    1.14
     worsening
    1.13
     progression
    1.13
     discontin
    1.12
     improvement
    1.10
     toler
    1.10
     efficacy
    1.09
    Activations Density 0.256%

    No Known Activations