© 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. 11-RES-JB
    11. 9483
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Morris

    oai_token-act-pair · gpt-3.5-turbo

    specific names and entities related to people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ç
    -1.01
     comet
    -0.87
     à¤
    -0.87
    Äģ
    -0.85
     asteroids
    -0.84
    abase
    -0.82
    Äĵ
    -0.81
     lav
    -0.79
    Cath
    -0.79
     pel
    -0.78
    POSITIVE LOGITS
    Mor
    2.54
     Morris
    2.51
     Mor
    1.86
     Moran
    1.63
    mor
    1.63
     Morrison
    1.60
     Morales
    1.46
     MOR
    1.40
     Morgan
    1.25
    Morgan
    1.23
    Activations Density 0.232%

    No Known Activations