© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 13815
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental entities

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IU
    -0.73
    jad
    -0.69
    terday
    -0.69
    vill
    -0.66
    card
    -0.66
    uously
    -0.65
    FACE
    -0.65
    cro
    -0.64
    uous
    -0.62
    aterasu
    -0.61
    POSITIVE LOGITS
     Accountability
    1.36
     Communications
    0.90
     Shutdown
    0.89
    vernment
    0.88
     Relations
    0.86
     Accounting
    0.78
     Employees
    0.74
     Panel
    0.73
     Publishing
    0.71
     Association
    0.70
    Activations Density 0.031%

    No Known Activations