© 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. 0-RES-JB
    11. 23220
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic display screens

    oai_token-act-pair · gpt-3.5-turbo

    references to screens and display technology

    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
    uilding
    -0.80
    za
    -0.77
    Relations
    -0.70
    wild
    -0.69
     winters
    -0.68
    Fed
    -0.65
     Hend
    -0.65
    ocene
    -0.64
    thood
    -0.64
    aci
    -0.64
    POSITIVE LOGITS
     screen
    3.84
    screen
    3.04
     screens
    2.97
     Screen
    2.84
    Screen
    2.77
    creen
    2.18
     screened
    1.52
     screenshot
    1.44
     touchscreen
    1.40
     screening
    1.40
    Activations Density 0.020%

    No Known Activations