© 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. 8-RES-JB
    11. 7917
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical terminology and technical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    negative terms or concepts related to health and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.69
    ings
    -0.64
    atche
    -0.62
    ows
    -0.62
     Nurse
    -0.61
     Pledge
    -0.60
    acious
    -0.59
     Griffin
    -0.59
     Burnett
    -0.58
     Fitzgerald
    -0.57
    POSITIVE LOGITS
    technical
    1.04
    centric
    1.03
    direction
    1.00
    political
    1.00
    tur
    1.00
    hazard
    1.00
    ther
    0.97
    electric
    0.97
    engineering
    0.94
    weekly
    0.94
    Activations Density 0.079%

    No Known Activations