© 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. 10-RES-JB
    11. 8531
    Prev
    Next
    INDEX
    Explanations

    organizations or groups associated with specific causes or ideologies, particularly those focused on politics or advocacy

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or groups advocating for specific political or social causes

    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
     veins
    -0.76
     churn
    -0.72
     circles
    -0.72
    mson
    -0.71
     glances
    -0.69
     aggrav
    -0.67
     rumours
    -0.66
     gorge
    -0.66
     quarters
    -0.65
     accent
    -0.64
    POSITIVE LOGITS
     Respons
    1.14
     Equality
    1.10
     Responsibility
    1.09
     Better
    1.04
     Change
    0.96
     Choice
    0.94
     Eth
    0.92
     Values
    0.88
     Reprodu
    0.88
     Peace
    0.87
    Activations Density 0.051%

    No Known Activations