© 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. 0-RES-JB
    11. 4813
    Prev
    Next
    INDEX
    Explanations

    words related to political figures specifically starting with "Ts"

    oai_token-act-pair · gpt-3.5-turbo

    references to Tsunami events or Tsunami-related terms

    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
    hyde
    -0.94
    joy
    -0.77
     fly
    -0.67
     leather
    -0.66
     FANTASY
    -0.64
    burn
    -0.64
    Denver
    -0.64
    hered
    -0.64
     stud
    -0.63
    becue
    -0.63
    POSITIVE LOGITS
     Ts
    3.97
    Ts
    2.82
     ts
    2.26
     Tsu
    1.45
     Kats
    1.38
     Kw
    1.37
     cz
    1.34
     tsun
    1.29
     Hok
    1.27
     tsunami
    1.27
    Activations Density 0.020%

    No Known Activations