© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5118
    Prev
    Next
    INDEX
    Explanations

    phrases related to embarrassing situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "embarrassing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ework
    -0.97
    ership
    -0.82
    igel
    -0.81
    WORK
    -0.80
    ingham
    -0.79
    enfranch
    -0.78
    erential
    -0.78
    elled
    -0.77
    elfare
    -0.76
    ello
    -0.76
    POSITIVE LOGITS
     embarrassing
    1.05
     embarrassment
    1.02
     humiliating
    0.92
     Haram
    0.84
     embarrass
    0.80
    faced
    0.78
     awkward
    0.75
     ABE
    0.74
     humiliation
    0.74
     silence
    0.74
    Activations Density 0.036%

    No Known Activations