© 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. 4-RES-JB
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to family relationships, especially those involving in-laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to familial relationships, specifically "in-law" connections

    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
    illac
    -0.74
     Chero
    -0.73
    HCR
    -0.70
    ħĭ
    -0.69
     AVG
    -0.68
    paio
    -0.67
     Extensions
    -0.63
    orem
    -0.63
    irements
    -0.62
     reps
    -0.61
    POSITIVE LOGITS
    sight
    0.92
    built
    0.88
    depth
    0.87
     guise
    0.87
    advert
    0.86
     midst
    0.84
    bound
    0.83
    development
    0.83
    direction
    0.82
    progress
    0.82
    Activations Density 0.032%

    No Known Activations