Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20272
    Prev
    Next
    INDEX
    Explanations

    mentions of socialist and socialism-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to socialist and communist ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.90
    ricanes
    -0.82
    croft
    -0.81
    trak
    -0.81
    staking
    -0.78
    uchin
    -0.74
    aunder
    -0.70
    xus
    -0.70
    emis
    -0.70
    WAYS
    -0.68
    POSITIVE LOGITS
     Equality
    0.83
     Worker
    0.78
     paradise
    0.77
     sympath
    0.77
     Socialist
    0.76
     socialist
    0.73
     Alternative
    0.73
     prisoner
    0.72
     socialists
    0.72
     Lenin
    0.70
    Activations Density 0.027%

    No Known Activations