© 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. 9-RES-JB
    11. 15096
    Prev
    Next
    INDEX
    Explanations

    words related to data storage or capacity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of storage and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.85
    inel
    -0.79
    atown
    -0.78
    sky
    -0.76
    unin
    -0.75
    ĪĴ
    -0.75
    ansson
    -0.73
    ler
    -0.71
    kok
    -0.71
    enegger
    -0.71
    POSITIVE LOGITS
     capacity
    1.01
     capacities
    0.96
     shelves
    0.95
     storage
    0.93
     devices
    0.91
     Spaces
    0.91
     depot
    0.88
     Devices
    0.85
     cabinets
    0.84
    istics
    0.82
    Activations Density 0.042%

    No Known Activations