© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    names of people and possibly locations, particularly from historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    names and historical references to prominent figures and their contributions

    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
    Tonight
    -0.84
    Yesterday
    -0.83
    Latest
    -0.82
    Asia
    -0.80
    blogs
    -0.79
    gpu
    -0.77
    ebin
    -0.75
    Results
    -0.74
    RELATED
    -0.74
    Last
    -0.71
    POSITIVE LOGITS
     Twain
    1.24
     Chamberlain
    1.21
     Mead
    1.21
     Whitman
    1.20
     Lovecraft
    1.19
     Rockefeller
    1.19
     Hubbard
    1.18
     Howe
    1.17
     Harding
    1.15
     Stevenson
    1.15
    Activations Density 0.335%

    No Known Activations