© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10194
    Prev
    Next
    INDEX
    Explanations

    words related to family relationships or siblings

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, particularly focusing on the term "brothers" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asive
    -0.70
    ivity
    -0.66
     Satisf
    -0.65
    ¨
    -0.65
    OTA
    -0.63
    urable
    -0.63
    ive
    -0.62
    VERTISEMENT
    -0.62
    GMT
    -0.61
    utt
    -0.61
    POSITIVE LOGITS
     brothers
    3.88
     sisters
    2.83
     siblings
    2.57
     Brothers
    2.49
    brother
    2.27
     brother
    2.23
     brethren
    2.11
    Brother
    2.05
     cousins
    2.02
     sons
    1.91
    Activations Density 0.020%

    No Known Activations