© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    words related to atomizers or electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to types of "izers" in various contexts, particularly in the context of medical and organizational references

    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
     Westminster
    -0.61
     cats
    -0.60
     NSW
    -0.57
     organisations
    -0.57
     severed
    -0.57
     Leap
    -0.57
     nationality
    -0.57
     cat
    -0.56
     formally
    -0.56
     Thames
    -0.56
    POSITIVE LOGITS
    izer
    4.61
    izers
    3.85
    iser
    2.64
    isers
    2.50
    izing
    2.27
    ize
    2.16
    ization
    2.12
    izes
    2.12
    ized
    2.01
    izations
    1.90
    Activations Density 0.007%

    No Known Activations