© 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 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. 10-RES-JB
    11. 4767
    Prev
    Next
    INDEX
    Explanations

    phrases related to information or situations becoming known to the public

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to revelations or discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.67
     Goo
    -0.66
    phia
    -0.65
     Loyal
    -0.61
    knife
    -0.60
     Caps
    -0.59
     advance
    -0.58
     Licensed
    -0.58
     Shu
    -0.58
     blackout
    -0.58
    POSITIVE LOGITS
     spontaneously
    1.07
     unexpectedly
    1.01
     naturally
    0.78
     suddenly
    0.77
     anew
    0.73
     again
    0.72
     mysteriously
    0.72
     sooner
    0.71
    river
    0.71
     handy
    0.70
    Activations Density 0.101%

    No Known Activations