Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 18759
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer components and accessories, such as power supply units (PSU), graphic cards, CPUs, coolers, amplifiers, SSDs, and drives

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to computer hardware components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prison
    -0.78
    prison
    -0.75
     boulder
    -0.67
    okemon
    -0.67
     Cind
    -0.67
    rians
    -0.66
     Pension
    -0.66
     bould
    -0.65
    CHA
    -0.65
     Bird
    -0.64
    POSITIVE LOGITS
     adapter
    1.08
     manufacturer
    1.08
     adapters
    1.00
     Adapter
    0.99
     heater
    0.98
     manufacturers
    0.98
     fitted
    0.95
     firmware
    0.95
     Asus
    0.94
     specs
    0.92
    Activations Density 0.211%

    No Known Activations