© 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. 8-RES-JB
    11. 17689
    Prev
    Next
    INDEX
    Explanations

    the name "Nik" with varying degrees of closeness to the full name "Nikolas"/"Nikolai"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Nik" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cellular
    -0.72
    dress
    -0.71
    cloth
    -0.71
     mainland
    -0.69
    pants
    -0.69
     SPORTS
    -0.62
    BACK
    -0.61
     Rainbow
    -0.61
     Monarch
    -0.59
    GROUND
    -0.59
    POSITIVE LOGITS
    aido
    1.26
    opol
    1.02
    olas
    0.99
    ita
    0.99
    elsen
    0.96
    ificent
    0.94
    iques
    0.94
    umar
    0.94
    iren
    0.92
    ola
    0.91
    Activations Density 0.045%

    No Known Activations