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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14238
    Prev
    Next
    INDEX
    Explanations

    code snippets related to web development

    oai_token-act-pair · gpt-3.5-turbo

    structured data, particularly related to programming concepts and application routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovecraft
    -0.86
     NTS
    -0.85
     Gillespie
    -0.82
     Falk
    -0.77
     Cald
    -0.76
     astronomers
    -0.75
    ocaust
    -0.75
     Kling
    -0.74
     kHz
    -0.74
    GGGG
    -0.71
    POSITIVE LOGITS
    Controller
    1.02
    controller
    1.01
     Rails
    0.92
     helper
    0.91
    Template
    0.91
    views
    0.90
     helpers
    0.90
    Http
    0.89
    Route
    0.89
    application
    0.89
    Activations Density 0.161%

    No Known Activations