© 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. 4-RES-JB
    11. 24017
    Prev
    Next
    INDEX
    Explanations

    the name "Karen" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Karen"

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

    No Comments

    Negative Logits
    etheus
    -0.81
     Logged
    -0.74
    cipline
    -0.74
    cision
    -0.73
    udic
    -0.70
    apore
    -0.67
    */(
    -0.67
    antly
    -0.65
    intelligence
    -0.65
    videos
    -0.65
    POSITIVE LOGITS
     Sue
    0.90
     Karen
    0.89
    aii
    0.81
     Bei
    0.78
    ites
    0.76
    ite
    0.72
     Borders
    0.72
    fman
    0.71
     Goodman
    0.71
     Kaufman
    0.69
    Activations Density 0.011%

    No Known Activations