© 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. 22329
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Japanese names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals with the surname 'Roshi'

    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
     Gazette
    -0.68
     reviews
    -0.65
     lim
    -0.63
     review
    -0.62
     Sed
    -0.60
     memoir
    -0.60
     emails
    -0.60
     Lat
    -0.59
     images
    -0.59
     Cour
    -0.59
    POSITIVE LOGITS
    oshi
    4.60
    osh
    1.38
    asu
    1.25
    uki
    1.19
    ogi
    1.19
    shi
    1.16
    omi
    1.06
     Yoshi
    1.06
    oday
    1.05
    ashi
    1.04
    Activations Density 0.008%

    No Known Activations