© 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. 10058
    Prev
    Next
    INDEX
    Explanations

    mentions of political ideologies or movements, specifically communism

    oai_token-act-pair · gpt-3.5-turbo

    references to 'communism' and 'communication'

    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
     tractor
    -0.86
     raids
    -0.81
     raid
    -0.74
     rake
    -0.74
     extraction
    -0.71
     keeper
    -0.70
     Slate
    -0.69
     extracts
    -0.69
     boots
    -0.68
     Mechdragon
    -0.67
    POSITIVE LOGITS
    commun
    3.92
    communication
    2.90
    Commun
    2.27
    communications
    2.05
     COMMUN
    1.39
     Commun
    1.26
    cong
    1.13
    social
    1.10
    compl
    1.07
     communism
    1.04
    Activations Density 0.034%

    No Known Activations