© 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. 4-RES-JB
    11. 625
    Prev
    Next
    INDEX
    Explanations

    close-up descriptions or mentions in text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to panoramic and close-up views or imagery

    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
     benefic
    -0.78
    responsible
    -0.77
     governing
    -0.74
    verning
    -0.72
     finance
    -0.71
    ccoli
    -0.71
     mailing
    -0.71
     withdrawing
    -0.70
     withdrawn
    -0.70
    conduct
    -0.68
    POSITIVE LOGITS
     visuals
    1.20
     footage
    1.19
     images
    1.18
     Thumbnails
    1.07
     photographs
    1.06
     imagery
    1.06
    oscopic
    1.03
     pictures
    1.02
    visual
    1.00
    Visual
    1.00
    Activations Density 0.306%

    No Known Activations