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

    Neuronpedia

    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. 4-RES-JB
    11. 11457
    Prev
    Next
    INDEX
    Explanations

    words related to advocacy and advocacy groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advocacy groups and their activities

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

    No Comments

    Negative Logits
    士
    -0.72
    agers
    -0.70
    ursed
    -0.69
     tranquil
    -0.68
    othes
    -0.68
    ilet
    -0.67
    orah
    -0.67
     Reincarn
    -0.66
    ãĥĥãĥī
    -0.64
    angers
    -0.63
    POSITIVE LOGITS
     advocacy
    1.04
     efforts
    0.87
     groups
    0.82
     organizations
    0.80
     NETWORK
    0.80
     campaigns
    0.78
    irtual
    0.78
    network
    0.78
     advocating
    0.77
     outreach
    0.77
    Activations Density 0.015%

    No Known Activations