© 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. 1-RES-JB
    11. 7168
    Prev
    Next
    INDEX
    Explanations

    words related to the aerospace industry and fields such as engineering, robotics, biomedical sciences, and poultry farming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various industries, particularly in manufacturing, aerospace, and biomedical fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.86
    heimer
    -0.73
    aries
    -0.71
    ifest
    -0.69
    tags
    -0.68
    oti
    -0.67
    plings
    -0.66
    oufl
    -0.66
     Recomm
    -0.65
    chens
    -0.65
    POSITIVE LOGITS
     aerospace
    1.13
     manufacturing
    1.11
     engineering
    1.10
     industry
    1.00
     practition
    0.99
     professionals
    0.99
     industries
    0.97
     firm
    0.91
     indust
    0.91
     entreprene
    0.89
    Activations Density 0.027%

    No Known Activations