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. 16193
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance data, perhaps related to computer hardware or benchmarks

    oai_token-act-pair · gpt-3.5-turbo

    numerical performance ratings and benchmarks

    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
     scapego
    -0.83
     bureaucratic
    -0.76
     deport
    -0.73
     Literary
    -0.71
     Harriet
    -0.71
     anarchist
    -0.71
     founding
    -0.70
     rab
    -0.70
     Pension
    -0.70
    Greek
    -0.70
    POSITIVE LOGITS
     overcl
    1.36
     Nvidia
    1.18
     fps
    1.18
     latency
    1.17
    fps
    1.17
     1080
    1.15
     benchmarks
    1.15
     throughput
    1.14
     ASUS
    1.12
    Battery
    1.11
    Activations Density 0.808%

    No Known Activations