© 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. 0-RES-JB
    11. 2440
    Prev
    Next
    INDEX
    Explanations

    medical conditions or negative situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ill" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clicker
    -0.82
     Tags
    -0.74
    jac
    -0.70
    sters
    -0.66
    rous
    -0.66
     Cour
    -0.66
    gor
    -0.65
     GPA
    -0.65
     Penet
    -0.64
     Brennan
    -0.64
    POSITIVE LOGITS
     ill
    3.61
     Ill
    1.68
     sick
    1.41
    Ill
    1.32
     illness
    1.29
     dise
    1.06
     illnesses
    1.06
     poorly
    1.04
     sickness
    1.01
     unjust
    0.97
    Activations Density 0.022%

    No Known Activations