© 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. 3-RES-JB
    11. 11264
    Prev
    Next
    INDEX
    Explanations

    keywords related to display screens technology, with a focus on LCD and OLED screens

    oai_token-act-pair · gpt-3.5-turbo

    references to display technologies, specifically LCD and OLED screens

    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
    女
    -0.93
    giving
    -0.84
    cific
    -0.77
    given
    -0.75
    rouse
    -0.73
    Downloadha
    -0.72
    REDACTED
    -0.72
    nell
    -0.72
    forth
    -0.71
    iyah
    -0.71
    POSITIVE LOGITS
     LCD
    0.94
     touchscreen
    0.93
     OLED
    0.92
     screens
    0.83
     TVs
    0.81
     monitors
    0.78
     screen
    0.77
     wallpaper
    0.74
     panels
    0.72
     targ
    0.71
    Activations Density 0.010%

    No Known Activations