© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 20480
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences discussing learning from experiences or mistakes

    oai_token-act-pair · gpt-3.5-turbo

    references to learning from past experiences or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.92
    atsu
    -0.89
    interstitial
    -0.89
    estate
    -0.88
    imo
    -0.86
    numbered
    -0.85
    mouth
    -0.84
    inence
    -0.83
    unless
    -0.83
    pei
    -0.80
    POSITIVE LOGITS
     afar
    1.01
     mistakes
    0.97
     lessons
    0.96
     experience
    0.90
     Lessons
    0.85
     whence
    0.84
     Experience
    0.81
     defeats
    0.80
     experiences
    0.80
     failures
    0.79
    Activations Density 0.104%

    No Known Activations