© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20673
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology devices and consumer choices

    oai_token-act-pair · gpt-3.5-turbo

    expressions of consumer needs and preferences regarding technology products

    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
     Rasmussen
    -0.82
     largeDownload
    -0.80
     contag
    -0.79
    sted
    -0.78
     Soros
    -0.76
     Transcript
    -0.74
    estern
    -0.74
     ãĤµ
    -0.74
    NJ
    -0.71
     Charity
    -0.71
    POSITIVE LOGITS
     laptops
    1.58
     touchscreen
    1.55
     laptop
    1.52
     MacBook
    1.49
     desktop
    1.49
     Chromebook
    1.44
     Lenovo
    1.43
    aptop
    1.41
     portable
    1.41
     hardware
    1.41
    Activations Density 0.647%

    No Known Activations