© 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. 2-RES-JB
    11. 9175
    Prev
    Next
    INDEX
    Explanations

    words related to coverings like veils and shrouds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to veils and covering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emort
    -0.87
    itialized
    -0.85
    pson
    -0.82
    ERAL
    -0.79
    ERG
    -0.78
    Unit
    -0.76
    oyal
    -0.75
    hesive
    -0.73
    olesc
    -0.71
    alogue
    -0.67
    POSITIVE LOGITS
     veil
    1.28
     veiled
    1.03
     Veil
    0.97
     shroud
    0.97
     maiden
    0.84
     cloaked
    0.82
     skirts
    0.80
     shrouded
    0.77
     cloak
    0.77
    cloth
    0.72
    Activations Density 0.012%

    No Known Activations