© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    instances where the word "when" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    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
    Grade
    -0.65
    agin
    -0.63
    Bas
    -0.61
    lander
    -0.61
    rolet
    -0.61
    aine
    -0.60
    sonian
    -0.59
    athom
    -0.58
    harm
    -0.58
    gem
    -0.58
    POSITIVE LOGITS
    soever
    1.39
    irlf
    0.83
    */(
    0.73
     confronted
    0.73
     pressed
    0.68
     asked
    0.68
     subjected
    0.67
     comparing
    0.63
     viewed
    0.63
     faced
    0.63
    Activations Density 0.111%

    No Known Activations