© 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. 1-RES-JB
    11. 16791
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific place or entity named "Regency"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Reg" as part of various terms or phrases related to regulations, regulatory agencies, or places

    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
    lihood
    -0.88
    hua
    -0.74
    =-=-
    -0.73
    CRIP
    -0.73
     Heavenly
    -0.69
     Hundred
    -0.66
    ÄŁ
    -0.65
     Tsu
    -0.65
     sake
    -0.64
     Benghazi
    -0.64
    POSITIVE LOGITS
    nant
    1.00
    ibr
    0.92
    inal
    0.92
    aud
    0.91
    ritional
    0.91
    aining
    0.90
    arded
    0.89
    olith
    0.89
    isters
    0.88
    rets
    0.87
    Activations Density 0.006%

    No Known Activations