© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17133
    Prev
    Next
    INDEX
    Explanations

    terms related to Domain Name System (DNS) operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to domain name service (DNS) and dynamic host configuration protocol (DHCP)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ships
    -0.80
    hunt
    -0.76
    ablishment
    -0.74
    odiac
    -0.74
    venant
    -0.73
    eton
    -0.71
    umar
    -0.69
    ovie
    -0.69
    eca
    -0.68
    esian
    -0.67
    POSITIVE LOGITS
     DNS
    1.07
     IPv
    0.93
    DAQ
    0.84
    ginx
    0.77
     congestion
    0.77
     spoof
    0.76
     DHCP
    0.76
    ython
    0.72
     amplification
    0.70
     claimant
    0.70
    Activations Density 0.011%

    No Known Activations