© 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. 8-RES-JB
    11. 17739
    Prev
    Next
    INDEX
    Explanations

    words related to connectivity or connection setups

    oai_token-act-pair · gpt-3.5-turbo

    references to network connections and connectivity devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.77
    sbm
    -0.76
    abal
    -0.73
    etti
    -0.70
    owell
    -0.69
    ãĤ«
    -0.68
    ItemThumbnailImage
    -0.67
    imental
    -0.65
     capit
    -0.64
    stad
    -0.63
    POSITIVE LOGITS
     servers
    1.06
     network
    1.05
     VPN
    1.01
     networks
    0.97
     WiFi
    0.95
     Ethernet
    0.93
     Bluetooth
    0.93
     Internet
    0.93
     server
    0.93
     devices
    0.92
    Activations Density 0.310%

    No Known Activations