© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20459
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to the design and purpose of technology or products

    oai_token-act-pair · gpt-3.5-turbo

    references to products or systems with a focus on their design and intended functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Charges
    -0.65
     Sussex
    -0.60
     Heard
    -0.57
    asta
    -0.56
    anches
    -0.56
     Ended
    -0.55
    oulos
    -0.55
     Figures
    -0.54
     laure
    -0.54
    Zone
    -0.53
    POSITIVE LOGITS
     specifically
    1.13
     expressly
    1.06
     to
    0.95
     specially
    0.90
     solely
    0.86
     primarily
    0.86
     accordingly
    0.82
     purely
    0.81
     for
    0.81
    irection
    0.80
    Activations Density 0.063%

    No Known Activations