© 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. 7011
    Prev
    Next
    INDEX
    Explanations

    proper names or entities, likely related to sports or news

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those involved in discussions or notable events

    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
    isure
    -0.78
    ewater
    -0.78
    lli
    -0.76
    atism
    -0.75
    agall
    -0.75
    emonium
    -0.75
    awaru
    -0.75
    estones
    -0.74
    packing
    -0.74
    starter
    -0.73
    POSITIVE LOGITS
     Jeremiah
    1.05
     Uriel
    0.87
     Grayson
    0.82
     Ezekiel
    0.81
     Ezra
    0.80
     Vaughan
    0.79
    miah
    0.78
     Amos
    0.77
     Koen
    0.77
     Hernandez
    0.76
    Activations Density 0.010%

    No Known Activations