© 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. 742
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or awareness of a situation

    oai_token-act-pair · gpt-3.5-turbo

    repetition of the word "knows" to indicate awareness or understanding

    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
    interstitial
    -0.88
    oples
    -0.88
    phrine
    -0.86
    otion
    -0.79
    ermanent
    -0.74
    isco
    -0.71
    phabet
    -0.69
    plet
    -0.68
    issions
    -0.68
    conservancy
    -0.67
    POSITIVE LOGITS
    ledged
    1.09
    ledge
    0.93
    LED
    0.86
    lege
    0.84
     how
    0.76
    nothing
    0.73
    ariat
    0.73
    terday
    0.72
     exactly
    0.72
    how
    0.72
    Activations Density 0.060%

    No Known Activations