© 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. 1-RES-JB
    11. 5224
    Prev
    Next
    INDEX
    Explanations

    instances of the word "poured"

    oai_token-act-pair · gpt-3.5-turbo

    actions related to pouring or spilling substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
    ization
    -0.75
    isation
    -0.73
    orth
    -0.72
    nesota
    -0.71
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    esp
    -0.66
    ALE
    -0.64
    ises
    -0.63
    istically
    -0.63
    POSITIVE LOGITS
     poured
    1.23
     pouring
    1.17
     encour
    1.08
     pour
    0.99
    pour
    0.86
     Pour
    0.86
     boiling
    0.79
     flowed
    0.74
    ĵĺ
    0.73
    renheit
    0.72
    Activations Density 0.013%

    No Known Activations