© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    words related to doing one's best or striving for excellence

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

    expressions of努力 and excellence

    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
    usted
    -0.78
    git
    -0.65
     Topic
    -0.65
    apter
    -0.65
     reverber
    -0.65
     outlawed
    -0.64
    devices
    -0.64
     reverted
    -0.61
     abolished
    -0.60
    ogene
    -0.60
    POSITIVE LOGITS
     imitation
    0.87
     efforts
    0.83
     approximation
    0.81
     endeav
    0.81
     effort
    0.80
     guess
    0.77
     selves
    0.77
    ial
    0.74
     impression
    0.73
    seller
    0.72
    Activations Density 0.040%

    No Known Activations