© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    government-related terms and titles, particularly those related to business and strategy

    oai_token-act-pair · gpt-3.5-turbo

    references to government and official titles or positions

    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
     boxed
    -0.69
     KILL
    -0.69
     tack
    -0.69
     itch
    -0.68
     pad
    -0.67
     molten
    -0.66
     detectable
    -0.66
     blister
    -0.65
     jerk
    -0.65
     nick
    -0.65
    POSITIVE LOGITS
     Fisheries
    1.19
    Environment
    1.17
     Tourism
    1.16
     Infrastructure
    1.14
    Commerce
    1.13
     Housing
    1.08
     Environment
    1.08
    rastructure
    1.07
    Education
    1.07
     Affairs
    1.06
    Activations Density 0.160%

    No Known Activations