© 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. 2-RES-JB
    11. 23883
    Prev
    Next
    INDEX
    Explanations

    instances where someone is declared dead

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pronounced," particularly in contexts related to death or declaration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sol
    -0.77
     Territories
    -0.75
     Straw
    -0.73
    ionage
    -0.73
    Labour
    -0.72
    Labor
    -0.71
     Camer
    -0.70
    hatt
    -0.68
    committee
    -0.65
    allows
    -0.64
    POSITIVE LOGITS
     pronounced
    0.99
     pronunciation
    0.88
     pronounce
    0.82
    senal
    0.82
     vowel
    0.78
     audible
    0.78
     spelling
    0.75
    aneously
    0.74
     notor
    0.72
     lav
    0.72
    Activations Density 0.007%

    No Known Activations