© 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. 3-RES-JB
    11. 9814
    Prev
    Next
    INDEX
    Explanations

    mentions of Non-Governmental Organizations (NGOs)

    oai_token-act-pair · gpt-3.5-turbo

    references to non-governmental organizations (NGOs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mith
    -0.81
    words
    -0.80
    berry
    -0.75
    bolt
    -0.74
    ipher
    -0.72
    manship
    -0.72
    othy
    -0.70
    croft
    -0.69
    ths
    -0.69
    apple
    -0.69
    POSITIVE LOGITS
     NGO
    0.90
    vernment
    0.88
    aily
    0.80
    BIL
    0.77
     bom
    0.77
    umbai
    0.76
     nomine
    0.72
     watchdog
    0.71
    IAS
    0.70
    culosis
    0.70
    Activations Density 0.005%

    No Known Activations