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. 3-RES-JB
    6. 10354
    Prev
    Next
    INDEX
    Explanations

    words related to Solid State Drives (SSDs) and RAID configurations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of solid-state drives (SSDs) and related technology terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.83
    ois
    -0.75
    nel
    -0.73
    govtrack
    -0.73
     Foley
    -0.69
     Australians
    -0.68
    yip
    -0.68
     UNESCO
    -0.67
     Paramount
    -0.67
     Boyle
    -0.67
    POSITIVE LOGITS
     SSD
    1.01
     storage
    0.89
     accelerator
    0.86
     HDD
    0.85
    DAQ
    0.82
    EED
    0.78
    MC
    0.78
    Ds
    0.78
     Specifications
    0.76
     capacities
    0.75
    Activations Density 0.009%

    No Known Activations