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

    Neuronpedia

    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. 2-RES-JB
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    references to male siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, specifically focusing on brothers and sisters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idine
    -0.64
    orie
    -0.64
    oval
    -0.63
    IV
    -0.62
    ebin
    -0.62
    ORE
    -0.62
    employment
    -0.62
    itation
    -0.61
    ģ
    -0.61
    ved
    -0.61
    POSITIVE LOGITS
     brothers
    1.13
     Brothers
    1.04
    hips
    1.01
    hip
    1.00
     sisters
    0.87
    pins
    0.85
    hift
    0.83
    omething
    0.82
    tones
    0.80
    pace
    0.79
    Activations Density 0.015%

    No Known Activations