© 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. 11-RES-JB
    11. 20648
    Prev
    Next
    INDEX
    Explanations

    keywords related to schools, colleges, and universities

    oai_token-act-pair · gpt-3.5-turbo

    references to education and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alys
    -0.90
    Austral
    -0.90
    Rum
    -0.78
     arte
    -0.76
    Mania
    -0.76
     Whilst
    -0.75
    clock
    -0.75
    âĹ¼
    -0.75
    oeuv
    -0.74
    bol
    -0.74
    POSITIVE LOGITS
     nonprofit
    1.47
     federally
    1.40
     nonprofits
    1.40
     statewide
    1.36
     charter
    1.34
     vocational
    1.23
     subsidized
    1.21
     accredited
    1.21
     voucher
    1.19
     municip
    1.19
    Activations Density 0.399%

    No Known Activations