Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15779
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Giuseppe" at varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Giovanna" or variations of that name

    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
    jri
    -0.68
    nikov
    -0.68
     Neh
    -0.63
    nesday
    -0.62
     Shutterstock
    -0.62
     Indian
    -0.60
     Prometheus
    -0.58
    leigh
    -0.58
     âĻ
    -0.58
    ioned
    -0.58
    POSITIVE LOGITS
    orno
    1.09
    udic
    0.99
    use
    0.96
    ord
    0.93
    uracy
    0.90
    vernment
    0.90
    ugi
    0.85
    otti
    0.83
    ust
    0.82
    ud
    0.82
    Activations Density 0.072%

    No Known Activations