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. 10-RES-JB
    6. 15672
    Prev
    Next
    INDEX
    Explanations

    phrases involving comparisons or relationships between two elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.72
    illin
    -0.64
    emed
    -0.59
    ¬¼
    -0.59
    anches
    -0.58
    emp
    -0.57
    idable
    -0.56
    raid
    -0.54
    icum
    -0.54
    closure
    -0.54
    POSITIVE LOGITS
     healthier
    0.92
     sooner
    0.75
     harder
    0.73
     louder
    0.71
     happier
    0.70
     easier
    0.70
     stronger
    0.70
     richer
    0.68
     fewer
    0.68
     smarter
    0.68
    Activations Density 0.043%

    No Known Activations