© 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. 9-RES-JB
    11. 7385
    Prev
    Next
    INDEX
    Explanations

    phrases related to hidden or secretive actions occurring out of public view

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or events occurring out of public view, particularly those that happen "behind closed doors."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TAMADRA
    -0.84
    gans
    -0.68
     Correction
    -0.65
    cision
    -0.64
    idays
    -0.58
     reproduce
    -0.57
     Solution
    -0.57
     pilgrimage
    -0.56
     redistributed
    -0.56
    nia
    -0.55
    POSITIVE LOGITS
    closed
    0.92
     closed
    0.90
     curtains
    0.80
     scenes
    0.78
     curtain
    0.78
     Scenes
    0.75
     doors
    0.75
    ãĤ«
    0.74
     Closed
    0.70
     Veil
    0.69
    Activations Density 0.147%

    No Known Activations