© 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. 22498
    Prev
    Next
    INDEX
    Explanations

    words related to oddity or unusualness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Odd" and its variations

    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
    ASE
    -0.99
    ASED
    -0.88
    tein
    -0.80
    ä¸Ń
    -0.77
    UNCH
    -0.74
    Interstitial
    -0.73
    ************
    -0.71
    Constructed
    -0.71
    assetsadobe
    -0.71
    DCS
    -0.70
    POSITIVE LOGITS
    yssey
    0.90
    swer
    0.85
    s
    0.82
     Odd
    0.81
    ness
    0.77
    lihood
    0.76
    shake
    0.74
    orp
    0.72
    rontal
    0.71
    sm
    0.70
    Activations Density 0.005%

    No Known Activations