© 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. 9-RES-JB
    11. 4152
    Prev
    Next
    INDEX
    Explanations

    dates and event descriptions

    oai_token-act-pair · gpt-3.5-turbo

    information related to specific dates, events, and celebrations

    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
     behav
    -0.69
    tein
    -0.66
    Years
    -0.65
     unethical
    -0.61
     nowadays
    -0.60
     secondly
    -0.60
    problem
    -0.58
     hereditary
    -0.58
     someday
    -0.57
     unemploy
    -0.57
    POSITIVE LOGITS
     fireworks
    1.00
     kickoff
    0.94
     festivities
    0.93
    Tickets
    0.88
     countdown
    0.88
     halftime
    0.86
    cade
    0.85
     livestream
    0.81
    Weather
    0.79
     midnight
    0.79
    Activations Density 1.108%

    No Known Activations