© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18689
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements and innovations, such as gaming, digital manufacturing, and quantum computing

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to industries and fields of study

    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
    osher
    -0.61
    itialized
    -0.60
    ussian
    -0.59
     clot
    -0.58
    ãĥ´
    -0.58
    umo
    -0.57
    isher
    -0.55
     Chocobo
    -0.55
    ellar
    -0.54
    cknowled
    -0.54
    POSITIVE LOGITS
    anship
    0.87
    ologies
    0.86
     practices
    0.84
    utics
    0.82
    smanship
    0.80
    istry
    0.79
     regimes
    0.76
    fare
    0.76
     schemes
    0.75
     techniques
    0.74
    Activations Density 0.477%

    No Known Activations