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. 2-RES-JB
    6. 16511
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to computer processors and technology

    oai_token-act-pair · gpt-3.5-turbo

    key technical specifications and performance benefits of computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jured
    -0.66
    accompanied
    -0.61
    nian
    -0.59
    fur
    -0.59
     prayed
    -0.59
     funer
    -0.57
     poems
    -0.57
    ghazi
    -0.57
    opathic
    -0.54
     Lump
    -0.54
    POSITIVE LOGITS
     SDK
    0.89
     Nvidia
    0.87
     Desktop
    0.85
     NVIDIA
    0.83
     chipset
    0.83
    software
    0.82
     Lenovo
    0.81
     IoT
    0.79
     Xiaomi
    0.79
     hardware
    0.78
    Activations Density 3.501%

    No Known Activations