© 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. 6-RES-JB
    11. 14773
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "Well,"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that conveys a pause or transition in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     footprint
    -0.68
    İĭ
    -0.67
    è¦ļéĨĴ
    -0.63
    atile
    -0.62
    emo
    -0.60
    shown
    -0.59
     vortex
    -0.59
     lightsaber
    -0.58
     cutter
    -0.58
     appliance
    -0.58
    POSITIVE LOGITS
     yeah
    1.02
    yeah
    0.92
     uh
    0.89
     yes
    0.85
     guess
    0.81
     hello
    0.79
     fortunately
    0.76
     sorry
    0.76
     thank
    0.75
     luckily
    0.75
    Activations Density 0.046%

    No Known Activations