© 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. 23529
    Prev
    Next
    INDEX
    Explanations

    physical characteristics and family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and dynamics

    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
    Players
    -0.71
     implementations
    -0.69
     Infrastructure
    -0.66
     infrastructure
    -0.65
     aggregate
    -0.65
     Strategic
    -0.64
     platforms
    -0.64
     substantive
    -0.64
     Regions
    -0.63
    éĹĺ
    -0.63
    POSITIVE LOGITS
    married
    1.15
    daughter
    1.11
    husband
    1.10
     Wife
    1.08
    wife
    1.08
     married
    1.04
     boyfriend
    1.04
     mom
    1.03
     girlfriend
    1.01
     sisters
    1.01
    Activations Density 0.746%

    No Known Activations