© 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. 11-RES-JB
    11. 9851
    Prev
    Next
    INDEX
    Explanations

    references to various data storage devices and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of computer storage devices and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EY
    -0.85
    ĨĴ
    -0.82
    yip
    -0.78
    naire
    -0.73
    enburg
    -0.69
    avia
    -0.69
    inel
    -0.69
    oria
    -0.68
    »
    -0.68
    £ı
    -0.67
    POSITIVE LOGITS
    disk
    1.33
     partitions
    1.21
    Disk
    1.21
     storage
    1.13
     SSD
    1.12
     disks
    1.12
     SATA
    1.09
     disk
    1.08
     HDD
    1.06
     filesystem
    1.04
    Activations Density 0.090%

    No Known Activations