© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    proper names or people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Lauren

    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
    */(
    -0.79
    lication
    -0.74
    LEASE
    -0.66
    Versions
    -0.65
     scorp
    -0.64
     neurot
    -0.64
     tempered
    -0.62
    Downloadha
    -0.61
    udeb
    -0.61
    icted
    -0.61
    POSITIVE LOGITS
    uren
    0.96
     Bac
    0.87
     Lauren
    0.84
    ists
    0.82
    ima
    0.80
     Faust
    0.79
     Greene
    0.75
    uthor
    0.75
    igue
    0.75
     Vander
    0.75
    Activations Density 0.013%

    No Known Activations