© 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. 3492
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and equipment

    oai_token-act-pair · gpt-3.5-turbo

    components related to mechanical devices and tools

    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
    nces
    -1.02
     demographics
    -0.90
    Ô
    -0.89
     territories
    -0.88
     Sins
    -0.87
     Authors
    -0.84
     victories
    -0.83
     Parties
    -0.82
     neighborhoods
    -0.82
     marriages
    -0.81
    POSITIVE LOGITS
     projector
    1.45
     recorder
    1.39
     charger
    1.37
     converter
    1.32
     controller
    1.30
     device
    1.30
     transmitter
    1.29
     generator
    1.27
    oscope
    1.25
     blaster
    1.25
    Activations Density 0.552%

    No Known Activations