© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    expressions related to accomplishment or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating success or achievement

    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
     caution
    -0.60
     weakness
    -0.54
    ãĥ¼ãĥ
    -0.54
     Juda
    -0.53
    ercise
    -0.53
     variable
    -0.53
    abling
    -0.52
     vig
    -0.52
    said
    -0.51
     availability
    -0.50
    POSITIVE LOGITS
     onto
    1.02
     ashore
    0.90
     into
    0.86
     thru
    0.86
    heast
    0.85
     through
    0.82
    cffffcc
    0.79
     Through
    0.79
     worthwhile
    0.77
     onstage
    0.76
    Activations Density 0.049%

    No Known Activations