© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6726
    Prev
    Next
    INDEX
    Explanations

    references to computer graphics rendering processes

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to 3D modeling and rendering processes

    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
     Hastings
    -0.83
     McCarthy
    -0.75
    issued
    -0.73
     custod
    -0.70
     Coleman
    -0.69
    rpm
    -0.69
     charitable
    -0.68
     Costco
    -0.68
     Sears
    -0.68
     Hubbard
    -0.67
    POSITIVE LOGITS
     shader
    1.56
     vertex
    1.38
    Textures
    1.35
     interpol
    1.33
     Texture
    1.29
    Animation
    1.28
     animation
    1.25
     sprite
    1.25
     animations
    1.22
     Animation
    1.22
    Activations Density 0.292%

    No Known Activations