© 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. 11-RES-JB
    11. 9989
    Prev
    Next
    INDEX
    Explanations

    researchers or scientists conducting studies and making discoveries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of researchers and scientists in the context of academic or scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.68
    âĢ¢âĢ¢
    -0.68
     ACTIONS
    -0.66
     Tactics
    -0.61
    times
    -0.61
     Flames
    -0.60
     Nationals
    -0.60
     patriotism
    -0.60
    Zip
    -0.59
    osite
    -0.59
    POSITIVE LOGITS
     studying
    1.25
     researching
    1.01
     specializing
    1.00
     investigating
    0.99
     probing
    0.98
     analyzing
    0.97
     conducting
    0.91
     collaborating
    0.90
     examining
    0.89
     hypothes
    0.87
    Activations Density 0.065%

    No Known Activations