© 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. 9-RES-JB
    11. 4333
    Prev
    Next
    INDEX
    Explanations

    information related to medical research subjects and analysis

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    think
    -0.77
    Scroll
    -0.77
    TextColor
    -0.75
     trillions
    -0.75
    atron
    -0.72
    Kick
    -0.71
    ulhu
    -0.70
    ioxide
    -0.69
    legraph
    -0.69
    Parts
    -0.69
    POSITIVE LOGITS
     âī¥
    1.31
     âĪ¼
    1.31
     âī¤
    1.18
     cohort
    1.12
     Patients
    1.11
     randomized
    1.11
     Participants
    1.10
     heterogeneity
    1.08
     phenotype
    1.03
     patients
    1.01
    Activations Density 0.975%

    No Known Activations