© 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. 11-RES-JB
    11. 6308
    Prev
    Next
    INDEX
    Explanations

    technology-related keywords, specifically related to companies like Cisco, IBM, and HP

    oai_token-act-pair · gpt-3.5-turbo

    references to major technology companies, particularly Cisco and IBM

    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
    pee
    -0.72
    draw
    -0.71
     deport
    -0.71
    chest
    -0.69
     sober
    -0.68
    bal
    -0.67
     starving
    -0.67
    genre
    -0.67
     empt
    -0.66
    nels
    -0.64
    POSITIVE LOGITS
     Corporation
    1.13
     Technologies
    1.13
     Labs
    1.11
     Electronics
    1.07
     Corp
    1.02
     Systems
    0.99
     patents
    0.97
     Technology
    0.96
     Laboratories
    0.94
     Computer
    0.94
    Activations Density 0.103%

    No Known Activations