© 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. 10-RES-JB
    11. 1246
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "moon."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "oon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rament
    -0.94
    ãĤ·ãĥ£
    -0.68
    APH
    -0.65
    senal
    -0.65
    kson
    -0.63
    Domin
    -0.63
     Ambro
    -0.62
    rd
    -0.62
    rocal
    -0.62
    PROV
    -0.62
    POSITIVE LOGITS
    zee
    1.04
    zees
    1.00
    er
    0.99
    igan
    0.98
    iverse
    0.95
    eri
    0.95
    igans
    0.94
    ishly
    0.93
    oola
    0.92
    ie
    0.89
    Activations Density 0.054%

    No Known Activations