Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11237
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly the proper noun "Kahn"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names and terms related to governance and law

    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
     Drac
    -0.96
     Bulgarian
    -0.82
    Leaks
    -0.80
     Bulgaria
    -0.80
    oir
    -0.79
    gypt
    -0.77
    Patch
    -0.76
    Greek
    -0.76
    rypt
    -0.76
    abama
    -0.74
    POSITIVE LOGITS
     Kahn
    3.61
     Lester
    1.46
     TED
    1.20
     NAFTA
    1.18
     Seymour
    1.12
     cane
    0.98
     Lennon
    0.98
     numer
    0.96
    gat
    0.87
    verning
    0.86
    Activations Density 0.066%

    No Known Activations