© 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. 0-RES-JB
    11. 9652
    Prev
    Next
    INDEX
    Explanations

    words related to proliferation, chiefly focused on the term 'proliferation' itself and its variations, as well as words related to politics and politicization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with nuclear proliferation and political issues

    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
    Redd
    -0.80
     Abdullah
    -0.77
     Duck
    -0.75
     Patron
    -0.72
    76561
    -0.70
     Reincarn
    -0.69
     Hood
    -0.68
     Kingdoms
    -0.68
     Cree
    -0.67
     Compan
    -0.67
    POSITIVE LOGITS
     proliferation
    2.00
    iferation
    1.71
     olig
    1.61
     politic
    1.34
    Gi
    1.24
     singled
    1.21
     glut
    1.20
     Gi
    1.13
     membrane
    1.05
     membranes
    1.05
    Activations Density 0.047%

    No Known Activations