© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13753
    Prev
    Next
    INDEX
    Explanations

    references to being on board or physically present in a specific place or vehicle

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "board" and related phrases indicating presence in a specific context

    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
    olson
    -0.81
    zel
    -0.76
    olver
    -0.69
    wig
    -0.68
    ãĤ¦ãĤ¹
    -0.67
    adem
    -0.65
     bund
    -0.65
    icity
    -0.63
    estic
    -0.63
    verb
    -0.62
    POSITIVE LOGITS
     HMS
    1.07
    boats
    0.96
     airplanes
    0.95
     USS
    0.89
     ships
    0.87
     ship
    0.87
     Voyager
    0.87
     Titanic
    0.87
     Flight
    0.86
     yacht
    0.85
    Activations Density 0.039%

    No Known Activations