© 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. 3-RES-JB
    11. 12396
    Prev
    Next
    INDEX
    Explanations

    words related to uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that begin with "Und" or "Unde," suggesting a focus on concepts related to uncertainty or undefined states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.76
    zzi
    -0.71
    âķIJâķIJ
    -0.70
    姫
    -0.69
    GY
    -0.69
    ppo
    -0.67
     FIRE
    -0.66
     Mahjong
    -0.65
    utic
    -0.65
    perature
    -0.64
    POSITIVE LOGITS
    efined
    1.10
    oubtedly
    1.04
    rawn
    1.03
    Und
    0.91
    ecided
    0.88
    ocumented
    0.86
    ications
    0.86
    raft
    0.85
    iscovered
    0.84
    rafted
    0.83
    Activations Density 0.005%

    No Known Activations