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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3127
    Prev
    Next
    INDEX
    Explanations

    keywords related to solid-state drives (SSDs) and related components such as SATA, RAID, and IDE

    oai_token-act-pair · gpt-3.5-turbo

    terms related to solid-state drives (SSDs) and their specifications

    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
    xon
    -0.86
     Australians
    -0.77
    bidden
    -0.77
     Boyle
    -0.75
    cko
    -0.74
    ois
    -0.72
     Kyr
    -0.72
    nel
    -0.71
     Warner
    -0.71
     Foley
    -0.71
    POSITIVE LOGITS
     SSD
    1.12
     HDD
    0.96
    PDATE
    0.87
     storage
    0.86
    ometimes
    0.82
    DAQ
    0.82
    Ds
    0.82
     accelerator
    0.81
     resil
    0.80
    idth
    0.75
    Activations Density 0.012%

    No Known Activations