© 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. 352
    Prev
    Next
    INDEX
    Explanations

    references to mysterious or enigmatic elements

    oai_token-act-pair · gpt-3.5-turbo

    references to "mystery" or concepts related to mystery

    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
    ibaba
    -0.82
    zar
    -0.80
    orses
    -0.80
    ript
    -0.79
    apsed
    -0.78
    amen
    -0.76
    arf
    -0.76
    obe
    -0.74
    inters
    -0.71
    baugh
    -0.71
    POSITIVE LOGITS
     Mystery
    1.02
     mystery
    0.98
     mysteries
    0.98
     solved
    0.90
     unsolved
    0.86
     Mysteries
    0.85
    stery
    0.80
     myster
    0.77
     Flavoring
    0.73
     shroud
    0.73
    Activations Density 0.012%

    No Known Activations