© 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. 9-RES-JB
    11. 16331
    Prev
    Next
    INDEX
    Explanations

    phrases related to broadband internet services and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to broadband internet services and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Judith
    -0.86
    nil
    -0.77
    orical
    -0.77
    orian
    -0.76
    otte
    -0.74
    gren
    -0.73
    pain
    -0.70
     Hitchcock
    -0.69
    lein
    -0.69
    orians
    -0.67
    POSITIVE LOGITS
     speeds
    1.29
     connectivity
    1.22
     routers
    1.04
     cables
    1.01
     providers
    0.98
     throughput
    0.97
     broadband
    0.94
     modem
    0.93
     optic
    0.93
     router
    0.92
    Activations Density 0.107%

    No Known Activations