© 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. 10-RES-JB
    11. 16637
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "this" is mentioned prominently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    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
    ARS
    -0.78
    utical
    -0.73
    letters
    -0.73
    okers
    -0.72
    aughtered
    -0.72
    arest
    -0.71
    hens
    -0.71
    acers
    -0.71
    pps
    -0.70
    asures
    -0.70
    POSITIVE LOGITS
     week
    0.99
     trope
    0.95
     applies
    0.91
     happens
    0.89
     morning
    0.88
     BEFORE
    0.86
     month
    0.86
     behaviour
    0.85
     phenomenon
    0.85
     anecd
    0.85
    Activations Density 0.080%

    No Known Activations