© 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. 12946
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of confusion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confusion" and related concepts

    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
    Interstitial
    -0.84
    ovy
    -0.82
    estone
    -0.74
    nesium
    -0.74
    rosse
    -0.71
    odes
    -0.70
    icle
    -0.70
    gans
    -0.68
    nam
    -0.67
    uscript
    -0.64
    POSITIVE LOGITS
     arising
    0.95
     stemming
    0.95
     arose
    0.93
     arises
    0.86
     confusion
    0.85
    lessness
    0.80
     regarding
    0.80
    fulness
    0.79
     shroud
    0.77
    lessly
    0.75
    Activations Density 0.040%

    No Known Activations