© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    `uated` and `punctuated` suffixes

    oai_token-act-pair · gpt-3.5-turbo

    words related to evaluation or assessment processes

    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
     Sin
    -0.63
     deal
    -0.61
     party
    -0.58
     bargain
    -0.56
     rights
    -0.56
     Solomon
    -0.55
     shout
    -0.55
     footprints
    -0.55
     stink
    -0.54
    TH
    -0.54
    POSITIVE LOGITS
    uated
    4.67
    uates
    3.42
    uate
    3.35
    uating
    3.31
    uation
    2.84
    uations
    2.25
    ually
    1.65
    uously
    1.44
    ivated
    1.38
    uality
    1.29
    Activations Density 0.012%

    No Known Activations