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. 7-RES-JB
    6. 5638
    Prev
    Next
    INDEX
    Explanations

    words related to electronics and specifically mentions of "EC" with varying numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to "EC" or "ECS" related to medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.81
    esthetic
    -0.73
     Jagu
    -0.72
    creen
    -0.72
     ç¥ŀ
    -0.71
    pocket
    -0.69
    tenance
    -0.68
     Swordsman
    -0.67
     Flavoring
    -0.66
     [+
    -0.64
    POSITIVE LOGITS
    MAS
    0.95
    outer
    0.94
    redits
    0.90
    ritical
    0.87
    ORD
    0.85
    overed
    0.85
    ERN
    0.82
    ounter
    0.81
    LECT
    0.80
    ANN
    0.79
    Activations Density 0.023%

    No Known Activations