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. 10-RES-JB
    6. 7566
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental institutions, particularly the Federal Communications Commission and the Federal Reserve

    oai_token-act-pair · gpt-3.5-turbo

    references to federal entities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IED
    -0.79
    sheets
    -0.75
    boxes
    -0.67
    ppard
    -0.67
    edin
    -0.67
    lies
    -0.67
    paces
    -0.67
    utra
    -0.66
    prototype
    -0.63
    heres
    -0.62
    POSITIVE LOGITS
     Reserve
    1.36
    ist
    0.99
     Communications
    0.97
     Aviation
    0.97
     Election
    0.97
     Trade
    0.96
     Bureau
    0.95
    ists
    0.94
     Register
    0.92
     Deposit
    0.91
    Activations Density 0.017%

    No Known Activations