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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22323
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person or character named "Got"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Got."

    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
    aire
    -0.65
    arry
    -0.63
     abound
    -0.63
    uate
    -0.61
    lite
    -0.60
     carpet
    -0.58
     entail
    -0.57
     entails
    -0.57
    ouston
    -0.56
    MM
    -0.56
    POSITIVE LOGITS
     Got
    3.81
    Got
    2.60
     GOT
    1.57
     Identified
    1.37
    got
    1.37
     Been
    1.31
     Learned
    1.29
     Gö
    1.25
     Went
    1.22
     Noticed
    1.22
    Activations Density 0.015%

    No Known Activations