© 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. 4-RES-JB
    11. 22139
    Prev
    Next
    INDEX
    Explanations

    IPv4 addresses and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to IP addresses and networking protocols

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

    No Comments

    Negative Logits
    arov
    -0.66
    igate
    -0.62
     whisk
    -0.61
    natureconservancy
    -0.61
    staff
    -0.60
     Mandal
    -0.60
     gunned
    -0.60
     snowball
    -0.59
    otrop
    -0.59
     starved
    -0.59
    POSITIVE LOGITS
    OGR
    0.81
    culosis
    0.76
    PORT
    0.75
    hyde
    0.74
    CLUS
    0.73
    VEN
    0.71
    TION
    0.71
    266
    0.70
    xus
    0.68
    IDE
    0.67
    Activations Density 0.054%

    No Known Activations