© 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. 1-RES-JB
    11. 3717
    Prev
    Next
    INDEX
    Explanations

    words related to darkness

    oai_token-act-pair · gpt-3.5-turbo

    instances and references to darkness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctions
    -0.90
    TAIN
    -0.81
     WATCHED
    -0.79
    GS
    -0.77
    INC
    -0.75
    IGN
    -0.75
    verett
    -0.75
    Union
    -0.75
    ction
    -0.75
    ta
    -0.74
    POSITIVE LOGITS
     darkness
    1.06
     shroud
    0.92
     destro
    0.89
     abyss
    0.87
    dark
    0.85
     reckoning
    0.82
     illum
    0.80
     overtake
    0.80
     shone
    0.79
     glare
    0.79
    Activations Density 0.013%

    No Known Activations