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. 11-RES-JB
    6. 7241
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal possessions or family relationships

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns related to familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.77
     similarly
    -0.73
     initially
    -0.72
     markedly
    -0.71
    imilar
    -0.71
     Typically
    -0.67
    often
    -0.67
    pract
    -0.66
     invariably
    -0.66
    nown
    -0.65
    POSITIVE LOGITS
     fuckin
    1.24
     soul
    1.21
     cunt
    1.20
     guts
    1.14
     fucking
    1.12
     pussy
    1.11
     goddamn
    1.10
     lungs
    1.09
     daddy
    1.07
     tits
    1.07
    Activations Density 0.256%

    No Known Activations