© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual reality technology and its components

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to virtual reality experiences and interactions

    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
     Rebell
    -0.82
     bankruptcy
    -0.74
    profits
    -0.73
     Nug
    -0.73
    Catholic
    -0.72
    otide
    -0.70
     surname
    -0.69
    priority
    -0.69
    Southern
    -0.68
     Preferred
    -0.68
    POSITIVE LOGITS
     immersive
    1.39
     simulated
    1.37
    reality
    1.34
     simulation
    1.31
     immersion
    1.27
     virtual
    1.27
     illusion
    1.25
     avatar
    1.22
     holog
    1.18
     simulations
    1.17
    Activations Density 0.595%

    No Known Activations