© 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 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. 9-RES-JB
    11. 19597
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing someone's right or entitlement to something

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or patterns that emphasize the concept of 'every' or 'all'

    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
     superiors
    -0.67
     subordinates
    -0.66
     judges
    -0.64
     whistleblowers
    -0.61
     Spani
    -0.59
     Judges
    -0.59
     jurors
    -0.57
     Americans
    -0.56
     retired
    -0.56
     Poles
    -0.56
    POSITIVE LOGITS
    initely
    0.77
    ̶
    0.73
    matter
    0.70
    ļéĨĴ
    0.69
    ĸļ
    0.69
    rying
    0.67
    probably
    0.67
    orm
    0.66
    rou
    0.66
    ala
    0.65
    Activations Density 0.866%

    No Known Activations