© 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. 7235
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "Taco"

    oai_token-act-pair · gpt-3.5-turbo

    brand names and specific terms associated with food and restaurants

    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
    lihood
    -1.04
    lessly
    -0.83
    hood
    -0.77
    theless
    -0.71
     FW
    -0.69
    HCR
    -0.69
    demand
    -0.68
     Wanted
    -0.67
     Applic
    -0.67
    soever
    -0.66
    POSITIVE LOGITS
    oco
    0.97
    otle
    0.97
    aco
    0.96
    eteria
    0.95
    ingu
    0.95
    anut
    0.94
    emia
    0.90
    cephal
    0.89
    osta
    0.89
    hetto
    0.88
    Activations Density 0.011%

    No Known Activations