© 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. 12-RES-JB
    11. 4183
    Prev
    Next
    INDEX
    Explanations

    phrases related to celebrations and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to celebrations and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apter
    -0.78
    iban
    -0.74
    ahon
    -0.74
    æ©Ł
    -0.73
    nery
    -0.72
    uggest
    -0.71
    voc
    -0.71
    ascript
    -0.69
    olit
    -0.69
    amar
    -0.68
    POSITIVE LOGITS
     Valentine
    0.97
     holidays
    0.95
     Thanksgiving
    0.95
     Independence
    0.94
     Eid
    0.90
     Christmas
    0.88
     Halloween
    0.85
     Birthday
    0.84
     birthday
    0.83
     diversity
    0.81
    Activations Density 0.126%

    No Known Activations