© 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. 8-RES-JB
    11. 3211
    Prev
    Next
    INDEX
    Explanations

    mentions of electronic devices, specifically smartphones like Samsung Galaxy models

    oai_token-act-pair · gpt-3.5-turbo

    references to specific smartphone models and their features

    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
    msg
    -0.84
     Scully
    -0.83
    opathic
    -0.71
    glers
    -0.68
     volunt
    -0.68
    gradient
    -0.67
    reek
    -0.67
     biologists
    -0.66
     âĸĪ
    -0.66
    ucl
    -0.65
    POSITIVE LOGITS
     Anniversary
    1.09
     successor
    0.85
     Compact
    0.85
     anniversary
    0.84
     Plus
    0.78
     XL
    0.78
     convertible
    0.74
     chipset
    0.73
     Mobility
    0.72
     debacle
    0.72
    Activations Density 0.099%

    No Known Activations