© 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. 4-RES-JB
    11. 20752
    Prev
    Next
    INDEX
    Explanations

    terms related to augmented reality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to augmented reality and its applications

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

    No Comments

    Negative Logits
    soDeliveryDate
    -0.84
    arding
    -0.77
    ESA
    -0.77
    ILLE
    -0.77
    psons
    -0.74
    inelli
    -0.72
     Club
    -0.68
    cats
    -0.67
    arded
    -0.66
    ilts
    -0.65
    POSITIVE LOGITS
    mented
    1.24
    mentation
    1.09
    ments
    0.98
    olon
    0.91
    ragon
    0.88
    thening
    0.86
    ality
    0.85
    allic
    0.81
     augmented
    0.74
    mental
    0.74
    Activations Density 0.023%

    No Known Activations