© 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. 3-RES-JB
    6. 23015
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude directed toward the recipient

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lau
    -0.67
    adjusted
    -0.67
    paper
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    options
    -0.65
    Mount
    -0.65
     Huntington
    -0.64
    claimed
    -0.63
     Gamb
    -0.62
    acular
    -0.62
    POSITIVE LOGITS
     guys
    1.18
    're
    1.10
     sir
    1.03
    tub
    1.01
     kindly
    0.96
    've
    0.86
    RS
    0.86
     know
    0.81
    'll
    0.80
     wish
    0.78
    Activations Density 0.046%

    No Known Activations