© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8620
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideology and governmental structures

    oai_token-act-pair · gpt-3.5-turbo

    sentences that discuss political ideologies, especially relating to socialism and capitalism

    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
    ributes
    -0.79
     quir
    -0.78
     donate
    -0.77
    ovember
    -0.74
    odo
    -0.74
    poke
    -0.73
     hug
    -0.73
     freezer
    -0.72
     volunte
    -0.71
     girlfriend
    -0.69
    POSITIVE LOGITS
     Hence
    1.41
     Therefore
    1.40
     Consequently
    1.38
     Thus
    1.37
     Moreover
    1.35
     Accordingly
    1.33
     Nevertheless
    1.31
     However
    1.25
     Furthermore
    1.24
     Whereas
    1.22
    Activations Density 1.124%

    No Known Activations