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. 10-RES-JB
    6. 12034
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data and technology

    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
    issues
    -0.88
    profits
    -0.77
     tragedies
    -0.76
    axies
    -0.76
    ongs
    -0.74
    Nazis
    -0.74
    projects
    -0.74
     rumors
    -0.74
    itters
    -0.73
     disasters
    -0.72
    POSITIVE LOGITS
     consisting
    1.23
     mechanism
    1.03
     whereby
    1.02
     arrangement
    1.02
     approach
    1.01
     format
    0.97
     comprising
    0.96
     system
    0.94
     structure
    0.93
     identifier
    0.93
    Activations Density 0.547%

    No Known Activations