© 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. 9519
    Prev
    Next
    INDEX
    Explanations

    words related to a specific object or concept that appears in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "element" in various contexts

    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
    hots
    -0.67
    straight
    -0.66
    puters
    -0.66
    Pitt
    -0.66
    graduate
    -0.65
    profits
    -0.63
     Speak
    -0.63
    Champ
    -0.62
    Shut
    -0.62
     Pictures
    -0.61
    POSITIVE LOGITS
     element
    3.74
     elements
    2.54
    element
    2.27
     Element
    2.19
     Elements
    1.81
     component
    1.70
     aspect
    1.66
    Element
    1.65
     dimension
    1.50
     factor
    1.36
    Activations Density 0.008%

    No Known Activations