© 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. 4-RES-JB
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "Und"

    oai_token-act-pair · gpt-3.5-turbo

    the term "und" and its variations, indicating uncertainty or vagueness in context

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

    No Comments

    Negative Logits
    姫
    -0.72
    fman
    -0.70
    zzi
    -0.69
     Mahjong
    -0.68
    ppo
    -0.67
    utic
    -0.67
    anwhile
    -0.66
    âķIJâķIJ
    -0.66
    olitan
    -0.66
     FIRE
    -0.64
    POSITIVE LOGITS
    oubtedly
    1.09
    efined
    1.07
    rawn
    1.02
    ecided
    1.01
    ocumented
    1.00
    rafted
    0.85
    erest
    0.83
    ications
    0.83
    efeated
    0.81
    iscovered
    0.79
    Activations Density 0.012%

    No Known Activations