© 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. 10-RES-JB
    11. 18805
    Prev
    Next
    INDEX
    Explanations

    words related to industrial processes and activities, such as mining, cultivation, processing, manufacturing, and refining

    oai_token-act-pair · gpt-3.5-turbo

    terms related to industrial and agricultural processes

    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
    maxwell
    -0.82
    urnal
    -0.82
    igmat
    -0.76
    earable
    -0.73
    IELD
    -0.71
    izophren
    -0.71
    ogn
    -0.70
    iven
    -0.70
    ognitive
    -0.70
    ohm
    -0.68
    POSITIVE LOGITS
     facilities
    1.30
     plants
    1.20
     techniques
    1.13
     sites
    1.12
     operations
    1.11
     ponds
    1.09
     methods
    1.07
     industries
    1.06
     facility
    1.06
     practices
    1.04
    Activations Density 0.206%

    No Known Activations