© 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. 21678
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to medical or health conditions

    oai_token-act-pair · gpt-3.5-turbo

    the frequent appearance of the substring "th"

    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
    ZA
    -0.62
     Clash
    -0.61
    INC
    -0.60
    ++++++++++++++++
    -0.59
     affairs
    -0.59
    GMT
    -0.57
     segregated
    -0.55
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.55
    ITED
    -0.54
     rake
    -0.54
    POSITIVE LOGITS
    ulhu
    1.47
    ttp
    1.41
    orne
    1.14
    umbnail
    1.08
    ousands
    1.07
    irteen
    1.07
    ousand
    1.05
    ieves
    1.05
    irty
    1.05
    istle
    1.04
    Activations Density 0.046%

    No Known Activations