© 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. 2-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    words related to traffic and transportation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and political structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.72
    é¾į
    -0.72
    apt
    -0.70
     vest
    -0.69
     suff
    -0.69
     bursting
    -0.65
    èª
    -0.61
     Wallace
    -0.59
    PRESS
    -0.59
    hers
    -0.59
    POSITIVE LOGITS
     Advice
    0.97
     Advisor
    0.83
     Coordinator
    0.81
    anyahu
    0.81
     Affairs
    0.80
    areth
    0.79
    uthor
    0.77
     Oversight
    0.77
     Advis
    0.77
     Regulatory
    0.74
    Activations Density 0.183%

    No Known Activations