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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 20838
    Prev
    Next
    INDEX
    Explanations

    features related to image editing and visual effects such as shadows, reflections, highlights, and transformations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to visual design and 3D modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.71
    financial
    -0.70
     confessions
    -0.68
     Bren
    -0.66
    adle
    -0.65
     Administ
    -0.63
    cigarettes
    -0.63
    abus
    -0.63
    ilitary
    -0.63
     administer
    -0.63
    POSITIVE LOGITS
     gradient
    1.09
     texture
    1.00
     axis
    0.98
     squares
    0.96
     width
    0.96
     triangles
    0.96
     shader
    0.95
     rectangle
    0.94
     geometry
    0.94
    RGB
    0.93
    Activations Density 0.331%

    No Known Activations