© 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. 8-RES-JB
    11. 6066
    Prev
    Next
    INDEX
    Explanations

    word groups related to surveillance and control

    oai_token-act-pair · gpt-3.5-turbo

    references to government surveillance and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aback
    -0.63
    Ĭ±
    -0.56
     sarcast
    -0.54
     dummy
    -0.54
    epad
    -0.54
     caveats
    -0.54
    oult
    -0.53
     joking
    -0.53
     caveat
    -0.53
     indicating
    -0.53
    POSITIVE LOGITS
     civilization
    0.90
     humankind
    0.83
     civilisation
    0.83
     mankind
    0.81
     humanity
    0.76
     imperialist
    0.75
     capitalism
    0.75
     industrialized
    0.74
     Capitalism
    0.74
     trillions
    0.73
    Activations Density 1.264%

    No Known Activations