© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20307
    Prev
    Next
    INDEX
    Explanations

    words related to the Communist Party

    oai_token-act-pair · gpt-3.5-turbo

    references to the Communist Party and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brach
    -0.81
     SPORTS
    -0.79
    Ocean
    -0.78
    ted
    -0.76
     Berks
    -0.68
    bos
    -0.67
    prise
    -0.67
    toe
    -0.67
    sweet
    -0.65
    esville
    -0.65
    POSITIVE LOGITS
     Manifest
    1.08
     dictatorship
    1.02
     Lenin
    1.00
     communists
    0.98
    Lenin
    0.98
     revolutionaries
    0.97
     Communists
    0.96
     insurgency
    0.91
     indoctr
    0.91
     dissidents
    0.89
    Activations Density 0.056%

    No Known Activations