© 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. 3-RES-JB
    11. 18235
    Prev
    Next
    INDEX
    Explanations

    phrases related to nonsensical or absurd statements

    oai_token-act-pair · gpt-3.5-turbo

    references to absurdity or irrationality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redits
    -0.76
    sole
    -0.74
    yer
    -0.73
    hani
    -0.72
    rosse
    -0.72
    bern
    -0.72
    vas
    -0.71
    nee
    -0.71
    ez
    -0.71
    irth
    -0.70
    POSITIVE LOGITS
     nonsense
    1.16
     gib
    0.85
     detector
    0.83
     guiActiveUn
    0.81
     bullshit
    0.81
    ishly
    0.77
     excuses
    0.74
     crap
    0.72
     misunderstand
    0.71
    mouth
    0.71
    Activations Density 0.012%

    No Known Activations