© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    phrases related to greetings and well wishes

    oai_token-act-pair · gpt-3.5-turbo

    greetings and expressions of good wishes

    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
     guiActiveUn
    -0.89
    è¦ļéĨĴ
    -0.76
    ĸļ
    -0.75
    otom
    -0.75
     Kron
    -0.69
    RANT
    -0.69
    ETH
    -0.67
    atars
    -0.65
     rall
    -0.65
    ewski
    -0.64
    POSITIVE LOGITS
     Mahjong
    0.70
     Audio
    0.69
     luck
    0.69
    mire
    0.68
     imitation
    0.66
    ãĤ¬
    0.65
     MPEG
    0.65
    ilda
    0.61
     978
    0.61
    cellence
    0.61
    Activations Density 0.093%

    No Known Activations