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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6970
    Prev
    Next
    INDEX
    Explanations

    instances where names ending with "son" are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    names or terms associated with familial relationships

    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
     urgently
    -0.68
     folds
    -0.67
     Fas
    -0.65
     Libre
    -0.65
     restraining
    -0.65
     Debbie
    -0.63
     toilet
    -0.62
     deb
    -0.62
     retreat
    -0.59
     tab
    -0.59
    POSITIVE LOGITS
    son
    4.62
    SON
    2.22
    sen
    1.94
    daughter
    1.86
    sson
    1.82
    sonian
    1.76
    father
    1.41
    Son
    1.33
    pson
    1.29
    kinson
    1.18
    Activations Density 0.016%

    No Known Activations