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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6734
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal or professional development and improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the process of becoming or achieving a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parting
    -0.70
     forbids
    -0.69
     teasing
    -0.66
     begs
    -0.65
    ages
    -0.64
     warning
    -0.64
     disagreement
    -0.63
    ongyang
    -0.62
     urging
    -0.61
     disadvant
    -0.61
    POSITIVE LOGITS
     proficient
    0.95
     successful
    0.91
     fluent
    0.90
     stronger
    0.85
     accustomed
    0.84
     acquainted
    0.83
     healthier
    0.82
     productive
    0.79
     wiser
    0.79
     masters
    0.78
    Activations Density 0.148%

    No Known Activations