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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11733
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and descriptions of characters in a story

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional states and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     scholarship
    -0.75
    itutional
    -0.75
     internationally
    -0.73
    Semitic
    -0.71
     attribution
    -0.70
     Sources
    -0.70
     biography
    -0.70
     endorsement
    -0.69
    definition
    -0.67
     Scholarship
    -0.67
    POSITIVE LOGITS
     gigg
    1.10
     stroll
    1.09
     chuck
    1.08
     smir
    1.06
     grabbed
    1.05
    Luckily
    1.03
     calmly
    1.01
     grinned
    1.00
     chuckled
    0.99
     luckily
    0.98
    Activations Density 0.740%

    No Known Activations