© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20028
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cinnamon"

    oai_token-act-pair · gpt-3.5-turbo

    references to cinnamon in various contexts

    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
    learning
    -0.71
    ebin
    -0.71
    SPONSORED
    -0.71
    lied
    -0.70
    lete
    -0.70
     Occupations
    -0.66
     ESC
    -0.65
    born
    -0.64
    hibited
    -0.64
     Applicant
    -0.63
    POSITIVE LOGITS
     cinnamon
    1.11
    nuts
    0.99
     grease
    0.91
    innamon
    0.91
     pudding
    0.87
     spice
    0.86
     rolls
    0.85
     wrapper
    0.84
     syrup
    0.83
    urous
    0.83
    Activations Density 0.010%

    No Known Activations