Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9685
    Prev
    Next
    INDEX
    Explanations

    HTTP-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to HTTP protocols and web communication

    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
    scene
    -0.71
    ynski
    -0.69
     Shepard
    -0.68
    teen
    -0.65
     Barkley
    -0.65
    ophy
    -0.64
     Photoshop
    -0.64
     Gong
    -0.64
    ighed
    -0.64
    vette
    -0.62
    POSITIVE LOGITS
    ://
    1.12
    Client
    1.08
    TPS
    1.05
    Connection
    1.03
    Http
    0.94
    Socket
    0.94
     handshake
    0.93
    Server
    0.91
     HTTP
    0.90
    Request
    0.90
    Activations Density 0.062%

    No Known Activations