© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    government departments and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific government departments or agencies

    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
     globally
    -0.96
     worldwide
    -0.86
     countries
    -0.81
     abroad
    -0.80
     domestically
    -0.80
     continents
    -0.78
     Tata
    -0.76
     global
    -0.75
     internationally
    -0.75
    Britain
    -0.75
    POSITIVE LOGITS
    bernatorial
    1.13
     Legislature
    1.08
     Sheriff
    1.07
     Lic
    1.06
     Penal
    1.02
     Trooper
    0.97
     Veter
    0.97
     Crimes
    0.96
     Prosecut
    0.95
     Police
    0.93
    Activations Density 0.176%

    No Known Activations