© 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. 4-RES-JB
    11. 7062
    Prev
    Next
    INDEX
    Explanations

    the word "met"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "met" in various contexts

    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
    etheless
    -0.69
    otine
    -0.64
     courier
    -0.63
     annex
    -0.63
    Jere
    -0.63
     nomine
    -0.62
    question
    -0.62
    rontal
    -0.61
    cember
    -0.61
     cone
    -0.61
    POSITIVE LOGITS
    amorph
    1.24
    ropolis
    1.12
    abus
    0.92
    tle
    0.90
    ropolitan
    0.90
    ered
    0.88
    yll
    0.85
    agame
    0.83
    allic
    0.82
    atars
    0.79
    Activations Density 0.016%

    No Known Activations