© 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. 9-RES-JB
    11. 7328
    Prev
    Next
    INDEX
    Explanations

    hydrocarbon compounds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ng"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.80
    ãĥ
    -0.74
    ãĥ¡
    -0.71
    ques
    -0.64
    toe
    -0.62
    UNCH
    -0.62
    ãĥ¢
    -0.62
     Fallen
    -0.61
    ises
    -0.60
    balls
    -0.60
    POSITIVE LOGITS
    oing
    1.17
    thening
    1.15
    allery
    1.12
    roups
    1.10
    thens
    1.06
    roup
    1.05
    lasses
    1.00
    raphics
    0.99
    inx
    0.93
    raph
    0.93
    Activations Density 0.045%

    No Known Activations