Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14026
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly uncles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of family members, specifically uncles and aunts

    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
    AMS
    -0.91
     Cognitive
    -0.73
    btn
    -0.68
    burst
    -0.68
    HR
    -0.67
     largeDownload
    -0.67
    vec
    -0.67
     Climate
    -0.66
     Cortex
    -0.65
     Crisis
    -0.64
    POSITIVE LOGITS
     uncle
    3.87
     aunt
    2.39
     Uncle
    2.18
     nephew
    2.05
    uncle
    2.05
     niece
    1.89
     grandfather
    1.71
     cousin
    1.70
     Aunt
    1.64
     grandmother
    1.52
    Activations Density 0.018%

    No Known Activations