© 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. 11-RES-JB
    11. 14299
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or groups in a social or political context

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal interactions and discussions about public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     è£ıè¦ļéĨĴ
    -0.74
    EStream
    -0.71
    ¶æ
    -0.68
    CLASSIFIED
    -0.67
    Þ
    -0.65
    ¿½
    -0.65
    ß
    -0.64
    [/
    -0.63
    ONSORED
    -0.63
    aditional
    -0.61
    POSITIVE LOGITS
    're
    1.03
     crave
    1.03
     adore
    0.93
    've
    0.90
     specialize
    0.89
     want
    0.89
     cherish
    0.88
     prioritize
    0.87
     lure
    0.87
     envision
    0.86
    Activations Density 0.652%

    No Known Activations