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. 3-RES-JB
    6. 1765
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    sentimental expressions related to emotions

    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
     tremend
    -0.70
    etheless
    -0.61
     plantation
    -0.60
     blender
    -0.59
    anwhile
    -0.58
     devise
    -0.57
     harvesting
    -0.57
     convergence
    -0.57
     planting
    -0.56
     maximizing
    -0.54
    POSITIVE LOGITS
    º
    1.00
    §
    0.97
    ¹
    0.95
    ı
    0.94
    »
    0.91
    ¡
    0.90
    ł
    0.88
    Ĵ
    0.87
    į
    0.86
    ¬
    0.86
    Activations Density 0.363%

    No Known Activations