© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    information related to health risks and medical conditions, specifically emphasizing vulnerability and risk factors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health risks, particularly those affecting specific populations

    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
    Reviewer
    -0.78
    çīĪ
    -0.76
    Revolution
    -0.74
     âĺ
    -0.74
    ileaks
    -0.71
     pandemonium
    -0.69
    Contract
    -0.67
     Expend
    -0.66
     è£ıç
    -0.65
    È
    -0.65
    POSITIVE LOGITS
     predis
    1.38
     autoimmune
    1.30
     genetics
    1.29
     diagnosed
    1.28
     diagnosis
    1.28
     symptoms
    1.27
     genetic
    1.24
     inflammation
    1.24
     diagnoses
    1.18
     obesity
    1.18
    Activations Density 0.380%

    No Known Activations