© 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. 9-RES-JB
    11. 18392
    Prev
    Next
    INDEX
    Explanations

    words related to computer hardware and software

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and computing processes

    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
    ovember
    -0.87
     summers
    -0.78
    igmat
    -0.77
     greatness
    -0.72
     disgrace
    -0.72
     winters
    -0.71
    luaj
    -0.71
     Skies
    -0.70
     understatement
    -0.70
     Klux
    -0.69
    POSITIVE LOGITS
     subsystem
    1.01
     node
    0.99
     transmitter
    0.97
     nodes
    0.95
     apparatus
    0.95
     transmitting
    0.91
     circuitry
    0.90
     operator
    0.87
     controller
    0.87
     receiver
    0.85
    Activations Density 0.493%

    No Known Activations