© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11058
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or conditions changing

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Until"

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

    No Comments

    Negative Logits
    hazard
    -0.73
    è¦ļéĨĴ
    -0.64
    æ©
    -0.63
    ItemImage
    -0.63
    PHOTOS
    -0.62
    qua
    -0.62
    eny
    -0.60
    pez
    -0.60
    pour
    -0.60
    cigarette
    -0.59
    POSITIVE LOGITS
    unda
    0.63
    ĸļ
    0.62
    orians
    0.62
    ulic
    0.61
     ende
    0.61
     Stats
    0.59
    omorph
    0.59
    memory
    0.59
    tt
    0.59
    inyl
    0.59
    Activations Density 0.023%

    No Known Activations