© 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. 0-RES-JB
    11. 10203
    Prev
    Next
    INDEX
    Explanations

    words related to screens or screen-related activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "screen" and its variations in the context of viewing or display

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     winters
    -0.70
     migr
    -0.60
     surplus
    -0.60
     Costa
    -0.60
     Hend
    -0.58
     Valent
    -0.58
     Esk
    -0.58
    ã
    -0.56
     frig
    -0.56
     named
    -0.56
    POSITIVE LOGITS
    screen
    4.32
    Screen
    2.59
     Screen
    2.47
     screen
    2.44
    creen
    2.30
     screens
    2.01
    panel
    1.51
    camera
    1.28
    stage
    1.27
     screened
    1.25
    Activations Density 0.015%

    No Known Activations