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. 4-RES-JB
    6. 20939
    Prev
    Next
    INDEX
    Explanations

    specific terms related to various fields, such as technology, nature, healthcare, and law

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various specific industries and sectors, particularly focusing on services, medical conditions, and finance

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

    No Comments

    Negative Logits
    terday
    -0.72
     tune
    -0.68
    ibly
    -0.67
     flask
    -0.65
    olson
    -0.65
     laughter
    -0.59
     favorable
    -0.59
     speaking
    -0.59
    rawdownloadcloneembedreportprint
    -0.59
     veiled
    -0.59
    POSITIVE LOGITS
     Consortium
    1.04
     Solutions
    1.01
     Services
    1.01
     Owners
    1.00
     Registry
    0.98
     Association
    0.97
     Operations
    0.97
     Dynamics
    0.97
     Maker
    0.96
     Partners
    0.96
    Activations Density 0.436%

    No Known Activations