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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1415
    Prev
    Next
    INDEX
    Explanations

    references to screen resolutions, especially 1080p

    oai_token-act-pair · gpt-3.5-turbo

    references to video resolution specifications

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

    No Comments

    Negative Logits
    uana
    -0.73
    leton
    -0.68
    notation
    -0.68
    eering
    -0.67
    stood
    -0.66
     synd
    -0.64
    atory
    -0.64
    uding
    -0.63
    leader
    -0.63
     administering
    -0.63
    POSITIVE LOGITS
     ILCS
    1.19
    1080
    0.87
     1080
    0.85
     CLIENT
    0.82
    °
    0.80
     CTR
    0.78
     Gems
    0.76
    IELD
    0.75
    eenth
    0.74
     Remastered
    0.72
    Activations Density 0.008%

    No Known Activations