© 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. 10-RES-JB
    11. 23411
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions and limitations

    oai_token-act-pair · gpt-3.5-turbo

    actions and conditions related to communication and physical capability

    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
     unwitting
    -0.62
    usra
    -0.57
    rather
    -0.56
    hat
    -0.56
    atto
    -0.55
     NEVER
    -0.54
    hoe
    -0.54
    rongh
    -0.52
    ãĤ©
    -0.52
    ãĥ©ãĥ³
    -0.52
    POSITIVE LOGITS
     anymore
    1.67
     adequately
    1.31
     properly
    1.27
     nor
    1.19
     efficiently
    1.09
     reliably
    1.07
     coherent
    1.05
     comfortably
    1.04
     satisf
    1.03
     safely
    1.01
    Activations Density 0.453%

    No Known Activations