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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1-RES-JB
    6. 20563
    Prev
    Next
    INDEX
    Explanations

    references to computer hardware components, specifically DDR RAM and Xeon processors, as well as terms related to overclocking such as 'overclocked'

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and references related to computer hardware and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lier
    -0.75
    leton
    -0.72
    jon
    -0.71
    liest
    -0.71
    atri
    -0.71
     Tigers
    -0.71
    opl
    -0.70
    eca
    -0.70
    alyses
    -0.70
     Samar
    -0.69
    POSITIVE LOGITS
     DDR
    1.24
     GDDR
    0.96
     disadvant
    0.82
     confir
    0.81
     glutamate
    0.76
    etheless
    0.74
     cryst
    0.72
    iversity
    0.71
    gradation
    0.70
     intrins
    0.69
    Activations Density 0.032%

    No Known Activations