© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15102
    Prev
    Next
    INDEX
    Explanations

    characteristics related to darkness

    oai_token-act-pair · gpt-3.5-turbo

    references to "dark."

    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
    oples
    -0.79
    ILA
    -0.78
    POR
    -0.78
    UTERS
    -0.77
    OPLE
    -0.76
    iphate
    -0.74
    ufact
    -0.72
    raltar
    -0.71
    utable
    -0.71
    essors
    -0.71
    POSITIVE LOGITS
    ening
    1.16
    ened
    1.11
    moon
    1.03
    hound
    0.90
    ener
    0.90
    lights
    0.87
     violet
    0.87
    dark
    0.86
     shadows
    0.85
    haired
    0.84
    Activations Density 0.011%

    No Known Activations