© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    verbs related to quick movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of urgent or hurried actions

    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
    Ranked
    -0.75
    iciency
    -0.69
     Continued
    -0.68
    nton
    -0.65
    cius
    -0.63
    oln
    -0.59
    illusion
    -0.59
    minus
    -0.58
    ãĥĩãĤ£
    -0.58
    ancy
    -0.58
    POSITIVE LOGITS
     onto
    0.94
     ashore
    0.94
     toward
    0.92
     forward
    0.91
     hither
    0.90
     blindly
    0.90
     overboard
    0.87
     into
    0.86
     towards
    0.86
     frantically
    0.84
    Activations Density 0.060%

    No Known Activations