© 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. 8-RES-JB
    11. 20421
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "honey" with varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to honey and its various forms or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.78
    ative
    -0.78
    osure
    -0.77
    uers
    -0.75
    ATIONS
    -0.70
    istical
    -0.69
    aneous
    -0.69
    ista
    -0.66
    uing
    -0.66
     Rite
    -0.65
    POSITIVE LOGITS
    moon
    1.48
    bees
    1.24
    comb
    1.19
    bee
    1.14
    pots
    1.00
    pot
    0.95
    bean
    0.94
    cot
    0.94
    beans
    0.93
    oney
    0.91
    Activations Density 0.035%

    No Known Activations