© 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. 0-RES-JB
    11. 11696
    Prev
    Next
    INDEX
    Explanations

    descriptions related to textures

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of various qualities or characteristics associated with texture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ans
    -0.78
     Communism
    -0.73
     Berk
    -0.68
    Capital
    -0.68
    mit
    -0.68
    inson
    -0.68
    aken
    -0.67
     Conf
    -0.67
    capital
    -0.66
     Pri
    -0.66
    POSITIVE LOGITS
     texture
    3.59
     textures
    3.16
     Texture
    2.58
    texture
    2.48
    Texture
    2.14
     shader
    1.67
    TEXTURE
    1.59
    Textures
    1.55
     shading
    1.40
     palette
    1.36
    Activations Density 0.024%

    No Known Activations