© 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. 8-RES-JB
    11. 22362
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating higher degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a comparative or incremental increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Procedures
    -0.71
     Provision
    -0.69
     Dreams
    -0.68
     Recording
    -0.68
     Commissioner
    -0.67
     Chips
    -0.66
     Records
    -0.66
     Travels
    -0.66
     Requirements
    -0.65
     Contracts
    -0.65
    POSITIVE LOGITS
     nuanced
    1.14
     sophisticated
    1.13
     complicated
    1.12
     elaborate
    1.10
     manageable
    1.10
     expansive
    1.09
     efficient
    1.07
     stringent
    1.06
     adventurous
    1.04
     drastic
    1.03
    Activations Density 0.089%

    No Known Activations