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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18872
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the tool or software "Sketch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of design concepts or software tools related to visual creation

    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
     guards
    -0.67
     planted
    -0.66
     pearl
    -0.66
     vigilant
    -0.63
     reg
    -0.63
     cooperative
    -0.63
     raiding
    -0.62
     divers
    -0.62
     resource
    -0.61
     reserve
    -0.60
    POSITIVE LOGITS
     Sketch
    4.40
     Illust
    1.33
    Shape
    1.29
     Premiere
    1.08
     Photoshop
    1.05
     Spray
    1.00
     Created
    0.97
    ï¸
    0.97
     Paint
    0.97
     sketches
    0.96
    Activations Density 0.025%

    No Known Activations