© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18212
    Prev
    Next
    INDEX
    Explanations

    mentions of family relations, particularly uncles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of family members, specifically uncles

    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
    mberg
    -0.96
    veyard
    -0.76
     largeDownload
    -0.73
    RH
    -0.69
    anchester
    -0.68
     Reprodu
    -0.67
     Featured
    -0.66
    anwhile
    -0.66
     Refugees
    -0.65
    Journal
    -0.65
    POSITIVE LOGITS
     uncle
    1.33
     aunt
    1.12
     nephew
    1.06
     niece
    1.01
     Uncle
    0.99
    liest
    0.91
    Dad
    0.85
     cousin
    0.82
    hetically
    0.81
     Aunt
    0.80
    Activations Density 0.008%

    No Known Activations