© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 7643
    Prev
    Next
    INDEX
    Explanations

    phrases related to administering or providing medical care/treatment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "administer" and its variations related to providing care or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ku
    -0.73
    Die
    -0.73
    wart
    -0.69
    faced
    -0.69
    faces
    -0.68
    Cache
    -0.67
    Secondly
    -0.66
    ritz
    -0.66
    âĢ¢âĢ¢
    -0.65
    Reason
    -0.65
    POSITIVE LOGITS
     administered
    1.36
     administering
    1.35
     administer
    1.32
     administ
    1.22
     administration
    0.82
     administr
    0.82
     helicop
    0.81
    administ
    0.81
     rul
    0.79
    utical
    0.76
    Activations Density 0.010%

    No Known Activations