© 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. 0-RES-JB
    11. 5380
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to servers

    oai_token-act-pair · gpt-3.5-turbo

    references to server-related technology and terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pawn
    -0.73
     dance
    -0.70
    lessly
    -0.69
     strike
    -0.69
    hattan
    -0.68
     sweep
    -0.68
     dances
    -0.67
     motions
    -0.67
     bicycle
    -0.67
     diversion
    -0.66
    POSITIVE LOGITS
     Server
    3.08
    Server
    2.15
    server
    1.41
     Client
    1.31
    Client
    1.15
    erver
    1.08
     Ser
    1.08
     Playoff
    0.98
     PowerShell
    0.96
     Simulator
    0.90
    Activations Density 0.019%

    No Known Activations