© 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. 10-RES-JB
    11. 13997
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly siblings

    oai_token-act-pair · gpt-3.5-turbo

    the term "brother" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acent
    -0.74
    ifact
    -0.72
    ocobo
    -0.67
    eneg
    -0.66
    erers
    -0.66
    ACA
    -0.64
    veyard
    -0.64
    issions
    -0.64
    tten
    -0.64
    Population
    -0.63
    POSITIVE LOGITS
    hood
    1.49
     brothers
    0.91
    ly
    0.89
     Nath
    0.82
     patriarch
    0.80
    brother
    0.78
    liness
    0.77
     brother
    0.77
     Brother
    0.75
     Uriel
    0.74
    Activations Density 0.039%

    No Known Activations