© 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. 8-RES-JB
    11. 20148
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific individuals or places, likely proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Pul" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.91
     Cassidy
    -0.73
    ãĢIJ
    -0.70
     Butterfly
    -0.68
     Organisation
    -0.67
    ele
    -0.66
     Leap
    -0.65
     Misty
    -0.64
    ELS
    -0.64
    ICLE
    -0.64
    POSITIVE LOGITS
    iple
    1.21
    monary
    1.17
    pees
    0.99
    gur
    0.97
    umin
    0.95
    rito
    0.88
    leted
    0.86
    inary
    0.86
    cery
    0.85
    cer
    0.84
    Activations Density 0.041%

    No Known Activations