© 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. 17121
    Prev
    Next
    INDEX
    Explanations

    I'm sorry, but I couldn't identify a specific pattern or theme based on the activations provided for Neuron 4

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "Burns" and associated entities

    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
    eanor
    -0.80
    iour
    -0.75
    rium
    -0.74
    ntil
    -0.72
    INAL
    -0.71
    ascal
    -0.69
    ffic
    -0.69
    ilial
    -0.68
     SLI
    -0.67
    agonist
    -0.67
    POSITIVE LOGITS
     Burns
    1.08
    LEY
    0.88
    leys
    0.78
     Burn
    0.78
    lee
    0.78
    ford
    0.78
    ville
    0.78
    leigh
    0.76
    ley
    0.74
    netflix
    0.74
    Activations Density 0.005%

    No Known Activations