© 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. 0-RES-JB
    6. 2222
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "new" with varying activations, possibly looking for specific references or contexts related to newness

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "new"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aggravated
    -0.66
     BASE
    -0.65
     pyramid
    -0.65
     cannabinoid
    -0.62
     principals
    -0.61
     convinced
    -0.61
     bases
    -0.60
     Spartan
    -0.60
     gain
    -0.60
     posit
    -0.59
    POSITIVE LOGITS
    ew
    4.38
    ews
    2.31
    EW
    1.75
    ewater
    1.54
    eworks
    1.40
    iw
    1.34
    eways
    1.32
    ework
    1.30
    ep
    1.27
    aw
    1.23
    Activations Density 0.016%

    No Known Activations