© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for words that end in "-is" and are related to positive qualities or compliments

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts, indicating assertions or states of being

    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
    ¥ŀ
    -0.93
    è¦ļéĨĴ
    -0.78
    ¥µ
    -0.73
     ABE
    -0.71
     reconc
    -0.68
     crates
    -0.67
    ruciating
    -0.66
     thumbnail
    -0.66
     entrances
    -0.65
     manners
    -0.64
    POSITIVE LOGITS
    abeth
    1.25
    peed
    1.06
    earch
    1.02
    olate
    1.01
    cience
    0.95
    olation
    0.95
    aurus
    0.94
    pect
    0.90
    ciplinary
    0.90
    terness
    0.87
    Activations Density 0.039%

    No Known Activations