© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10375
    Prev
    Next
    INDEX
    Explanations

    words related to authority, control, or forceful actions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "whip" and its contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.84
     Grateful
    -0.79
    alg
    -0.74
    ulia
    -0.69
    Fort
    -0.69
     Purpose
    -0.66
    Merit
    -0.66
    Attempts
    -0.64
    rio
    -0.63
    iquette
    -0.63
    POSITIVE LOGITS
     whip
    1.45
     whipping
    1.24
     Whip
    1.22
     whipped
    1.00
    otine
    0.88
    toe
    0.85
    ings
    0.80
     stitch
    0.79
     lash
    0.78
    boarding
    0.77
    Activations Density 0.006%

    No Known Activations