© 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. 12558
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gianis"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Gian" in various contexts, primarily associated with sports

    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
    loss
    -0.72
     UID
    -0.69
    District
    -0.64
    Trend
    -0.61
    legram
    -0.61
    etition
    -0.60
     Shame
    -0.59
    %"
    -0.59
     Opportunity
    -0.59
    bearing
    -0.59
    POSITIVE LOGITS
    nis
    1.49
    eman
    0.87
    aurus
    0.83
    emen
    0.83
    quad
    0.81
    ciplinary
    0.80
    ervative
    0.78
    hao
    0.78
    peed
    0.77
    pell
    0.76
    Activations Density 0.008%

    No Known Activations