© 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. 10-RES-JB
    6. 23267
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, particularly sons with varying levels of focus on them

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, specifically related to sons

    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
    veyard
    -0.70
    Population
    -0.70
    Union
    -0.69
     freight
    -0.65
     manifold
    -0.65
    Women
    -0.64
    ources
    -0.61
     locals
    -0.61
    Client
    -0.59
    ylon
    -0.59
    POSITIVE LOGITS
     Barron
    1.13
     Beau
    0.99
    ogram
    0.94
     Archie
    0.94
     Rory
    0.92
     Nathan
    0.92
     Caleb
    0.91
     Ethan
    0.89
     Eric
    0.89
     Toby
    0.89
    Activations Density 0.047%

    No Known Activations