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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17427
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and movements, specifically focusing on proletarian struggle and socialist principles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Marxist theory and class struggle

    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
    Pokemon
    -0.92
    ï¸ı
    -0.89
    Alert
    -0.87
    Buzz
    -0.86
     pricey
    -0.81
    ĵĺ
    -0.80
     HIP
    -0.79
    Pokémon
    -0.77
     prank
    -0.76
    poke
    -0.75
    POSITIVE LOGITS
     anarchism
    1.08
     Anarch
    1.03
     histor
    1.01
     anarchist
    1.00
     repression
    0.96
     proletariat
    0.95
     Marxist
    0.95
     organis
    0.95
     Marxism
    0.95
     Socialist
    0.94
    Activations Density 0.650%

    No Known Activations