© 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. 6-RES-JB
    11. 1575
    Prev
    Next
    INDEX
    Explanations

    verbs related to the development or use of tools or technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tools and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deen
    -0.83
     Examination
    -0.71
    united
    -0.71
     Deaths
    -0.67
     Pension
    -0.66
     Queens
    -0.64
     Nurs
    -0.64
     Meeting
    -0.64
    wic
    -0.63
     Confederation
    -0.62
    POSITIVE LOGITS
     patented
    0.95
     automate
    0.91
     algorithms
    0.82
     advancements
    0.82
     gadgets
    0.82
    software
    0.81
     detectors
    0.81
     enabling
    0.80
     enable
    0.80
     powering
    0.80
    Activations Density 0.567%

    No Known Activations