© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    the word "drum" and related words

    oai_token-act-pair · gpt-3.5-turbo

    references to drums and drumming

    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
     Tasman
    -0.68
    hiro
    -0.68
     Haram
    -0.67
     Govern
    -0.66
    actionDate
    -0.63
     Hydro
    -0.62
     Mandela
    -0.61
     Morales
    -0.61
    ################
    -0.60
    Ļ½
    -0.60
    POSITIVE LOGITS
    mers
    1.49
    ming
    1.43
    sticks
    1.24
    beat
    1.14
    mond
    1.13
    stick
    1.09
    med
    1.07
    sonian
    1.07
    nas
    1.06
    mer
    1.03
    Activations Density 0.027%

    No Known Activations