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. 0-RES-JB
    6. 3989
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Bolshevik" or related keywords

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the Bolshevik movement and communism

    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
    anguage
    -1.01
    ensing
    -0.80
    ensitive
    -0.78
    encies
    -0.78
    itiveness
    -0.76
    asar
    -0.76
    ENC
    -0.75
    ency
    -0.72
    ENCY
    -0.72
    ense
    -0.72
    POSITIVE LOGITS
     Bolshe
    1.85
     bol
    1.74
     Bolshevik
    1.43
    Sov
    0.90
     Communism
    0.88
     Communists
    0.80
     proletarian
    0.78
     negro
    0.73
     Lenin
    0.72
    selves
    0.72
    Activations Density 0.006%

    No Known Activations