© 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. 20807
    Prev
    Next
    INDEX
    Explanations

    the word "illusion" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to illusions and delusions

    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
    vez
    -0.67
    annis
    -0.64
    poon
    -0.64
    foreseen
    -0.64
    MIT
    -0.63
    nard
    -0.63
     Issues
    -0.61
    gars
    -0.60
    mins
    -0.59
    uled
    -0.59
    POSITIVE LOGITS
     illusion
    1.03
    ually
    1.01
    istically
    0.94
     Illusion
    0.93
     mir
    0.89
     illusions
    0.88
    ary
    0.88
    istical
    0.84
    arial
    0.82
    ual
    0.80
    Activations Density 0.025%

    No Known Activations