© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    phrases related to pumps and pumping actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pumping mechanisms or operations

    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
    lihood
    -0.82
    ournal
    -0.70
    BuyableInstoreAndOnline
    -0.70
    ########
    -0.68
    DragonMagazine
    -0.64
    ####
    -0.63
    Ĥİ
    -0.63
    rance
    -0.62
     Conquer
    -0.61
     distingu
    -0.61
    POSITIVE LOGITS
    kins
    1.16
     pump
    0.86
     pumps
    0.85
     pumping
    0.82
    oline
    0.81
    hetamine
    0.80
     inhibitors
    0.79
    kin
    0.79
    hift
    0.77
     inhibitor
    0.74
    Activations Density 0.049%

    No Known Activations