© 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 EvalsExportsinterp-engineNEWAPI 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. 5991
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use or application of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" in various contexts

    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
     Barg
    -0.70
     Entry
    -0.63
     Zur
    -0.58
    furt
    -0.54
     congratulations
    -0.53
     Sandwich
    -0.52
     hopeful
    -0.51
     Hai
    -0.51
    bitious
    -0.51
     Nas
    -0.50
    POSITIVE LOGITS
    fulness
    1.25
    cases
    1.23
    fully
    1.15
     cases
    1.11
    full
    1.11
    FUL
    1.10
     Cases
    1.09
    case
    1.03
    ful
    0.97
     case
    0.94
    Activations Density 0.079%

    No Known Activations