© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 2024
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that contain the substring "Ing"

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "ing" or gerunds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ģĸ
    -0.68
    IPS
    -0.65
    ajor
    -0.65
     digitally
    -0.65
    osh
    -0.64
    versions
    -0.64
    reet
    -0.63
     PSP
    -0.62
    ocks
    -0.62
     par
    -0.62
    POSITIVE LOGITS
     Ing
    4.43
    Ing
    2.46
     Dag
    1.36
     Ingram
    1.16
     Ingredients
    1.14
     ing
    1.12
     ingred
    1.11
     Tin
    1.08
     Ore
    1.06
     Og
    1.05
    Activations Density 0.028%

    No Known Activations