© 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. 10-RES-JB
    11. 10232
    Prev
    Next
    INDEX
    Explanations

    words related to machines, technology, and equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to machines, specifically in the context of military or industrial applications

    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
    alez
    -0.81
    raints
    -0.79
    orb
    -0.71
    uating
    -0.70
    uds
    -0.68
    bors
    -0.67
    uates
    -0.67
    omes
    -0.67
     sqor
    -0.66
    si
    -0.65
    POSITIVE LOGITS
    gun
    1.21
    guns
    1.06
     readable
    0.95
    anical
    0.82
     learning
    0.82
    learning
    0.82
     guns
    0.78
     Learning
    0.77
    chnology
    0.76
     gun
    0.75
    Activations Density 0.031%

    No Known Activations