© 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. 10522
    Prev
    Next
    INDEX
    Explanations

    media-related terms in text

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of media

    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
    ãĤ¡
    -0.72
    cker
    -0.67
    gling
    -0.65
     damn
    -0.63
     Hoover
    -0.62
    vasive
    -0.62
     Nigerian
    -0.61
    bats
    -0.61
     Salvador
    -0.61
     Frenchman
    -0.60
    POSITIVE LOGITS
    eval
    1.29
    wiki
    0.94
     outlets
    0.87
     literacy
    0.82
    media
    0.80
    medi
    0.76
     mog
    0.74
     caption
    0.72
    assets
    0.71
     conglomer
    0.71
    Activations Density 0.026%

    No Known Activations