© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    6. 3667
    Prev
    Next
    INDEX
    Explanations

    keywords related to server deployments and technical tasks

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to server deployment and configuration

    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
     Hanson
    -0.55
     Tanz
    -0.54
     Paula
    -0.51
     Goldstein
    -0.51
     Dough
    -0.51
    ogie
    -0.50
     Ally
    -0.50
     Willie
    -0.49
     reckoned
    -0.49
     Carrie
    -0.49
    POSITIVE LOGITS
     macOS
    0.97
     HTTP
    0.97
     filesystem
    0.95
     systemd
    0.94
     MySQL
    0.94
     APIs
    0.93
     plugins
    0.93
     sandbox
    0.92
    HTTP
    0.92
     debugger
    0.92
    Activations Density 0.694%

    No Known Activations