© 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. 4-RES-JB
    11. 10480
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and anatomical parts, specifically focusing on ACL surgery and eyelids

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ligands and medical conditions

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

    No Comments

    Negative Logits
     Riding
    -0.75
    Discussion
    -0.67
     Neutral
    -0.66
     Opportunity
    -0.66
     Median
    -0.65
     Worldwide
    -0.65
     Prosper
    -0.64
     Teach
    -0.64
     Virgin
    -0.64
     Planning
    -0.64
    POSITIVE LOGITS
    atures
    1.23
    ature
    1.15
    aments
    1.05
     lig
    0.98
    ations
    0.93
    ament
    0.92
     acids
    0.91
    atory
    0.91
    ures
    0.90
    uers
    0.90
    Activations Density 0.014%

    No Known Activations