© 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. 20683
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of formal agreements or arrangements

    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
    past
    -0.67
    clamation
    -0.66
    ãĥ©ãĥ³
    -0.65
    iesta
    -0.65
     thirsty
    -0.64
    prints
    -0.64
    hammad
    -0.62
    asters
    -0.62
    pson
    -0.62
    ogging
    -0.62
    POSITIVE LOGITS
     arrangements
    1.16
     arrangement
    1.09
     arrang
    1.06
    ally
    0.95
    owship
    0.77
    eering
    0.75
     arranged
    0.74
    etting
    0.73
     arranging
    0.73
    ords
    0.73
    Activations Density 0.011%

    No Known Activations