© 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. 10-RES-JB
    11. 10561
    Prev
    Next
    INDEX
    Explanations

    references to solid-state drives (SSDs) and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    information related to storage devices and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chu
    -0.87
    utra
    -0.84
     animate
    -0.81
     salute
    -0.81
     Witt
    -0.79
     offended
    -0.78
     ðŁij
    -0.78
     Nieto
    -0.78
     satir
    -0.76
     satire
    -0.75
    POSITIVE LOGITS
     SSD
    1.79
     HDD
    1.77
     RAID
    1.69
     SATA
    1.63
     storage
    1.59
     Storage
    1.51
     disks
    1.50
    Storage
    1.40
     disk
    1.39
    Disk
    1.39
    Activations Density 0.136%

    No Known Activations