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. 4-RES-JB
    6. 17445
    Prev
    Next
    INDEX
    Explanations

    computer graphics-related terms and techniques

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 3D rendering techniques and graphics

    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
    llah
    -0.79
    ership
    -0.78
    olla
    -0.73
    worth
    -0.69
    stood
    -0.69
    coni
    -0.68
    agall
    -0.67
    ffer
    -0.67
    abo
    -0.66
    meet
    -0.65
    POSITIVE LOGITS
     shader
    1.25
     Texture
    1.21
    Textures
    1.19
    Texture
    1.08
     plugin
    0.99
     textures
    0.99
    texture
    0.97
     Plugin
    0.97
     mapping
    0.96
     Painter
    0.96
    Activations Density 0.147%

    No Known Activations