© 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. 15709
    Prev
    Next
    INDEX
    Explanations

    terms and names related to psychiatry and medical specialties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical specializations, particularly in the context of psychiatric and pediatric medicine

    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
     tears
    -0.73
     Green
    -0.67
     intensity
    -0.65
     Owens
    -0.64
     level
    -0.63
     scissors
    -0.61
     knife
    -0.60
     cursor
    -0.60
     purple
    -0.59
    ple
    -0.59
    POSITIVE LOGITS
    iat
    4.56
    iatric
    2.03
    iatrics
    1.39
    iator
    1.36
    iate
    1.29
    ias
    1.20
    iatus
    1.18
    iac
    1.12
    iation
    1.10
    iations
    1.09
    Activations Density 0.012%

    No Known Activations