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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 12592
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Patrick" or words that contain "ric"

    oai_token-act-pair · gpt-3.5-turbo

    words related to "ric," possibly referencing specific names or terms associated with certain contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.73
    £ı
    -0.72
     Whale
    -0.72
    uyomi
    -0.69
    irk
    -0.64
     Emanuel
    -0.64
    skirts
    -0.61
    manuel
    -0.60
     Cosponsors
    -0.60
     Mara
    -0.59
    POSITIVE LOGITS
    ultural
    1.08
    chio
    1.03
    ycle
    1.02
    ulously
    0.99
    ulum
    0.98
     acid
    0.95
    ulture
    0.94
    hes
    0.93
     Acid
    0.90
    ourt
    0.86
    Activations Density 0.060%

    No Known Activations