© 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. 2-RES-JB
    11. 5711
    Prev
    Next
    INDEX
    Explanations

    the name "Mikael" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹
    -0.80
     GF
    -0.66
     UP
    -0.66
    enegger
    -0.64
    ALK
    -0.64
    uyomi
    -0.64
    ODUCT
    -0.62
     SG
    -0.62
     HIS
    -0.62
    atari
    -0.61
    POSITIVE LOGITS
    ael
    1.11
    itic
    0.92
    theless
    0.91
    izabeth
    0.90
    itism
    0.85
    iffe
    0.85
    iton
    0.84
    imal
    0.84
     destro
    0.82
    uate
    0.81
    Activations Density 0.002%

    No Known Activations