© 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. 7468
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, likely related to people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the name Enrique

    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
    robe
    -0.69
     tigers
    -0.68
    rums
    -0.64
    ramid
    -0.64
     skelet
    -0.64
     sled
    -0.63
    reference
    -0.62
    yrinth
    -0.62
    rog
    -0.62
    ulative
    -0.62
    POSITIVE LOGITS
    terday
    1.02
    cius
    0.91
    jamin
    0.88
    ignt
    0.85
    vironment
    0.81
    CRIPTION
    0.79
    Ò
    0.78
     Moines
    0.78
    istence
    0.77
    kt
    0.74
    Activations Density 0.012%

    No Known Activations