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. 8-RES-JB
    6. 18340
    Prev
    Next
    INDEX
    Explanations

    words related to dating and relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dating and romantic relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recoil
    -0.82
    Downloadha
    -0.80
     Flavoring
    -0.77
    £ı
    -0.77
    Reviewer
    -0.75
    eco
    -0.72
    ocument
    -0.72
    æ©Ł
    -0.72
    ulic
    -0.72
     Printed
    -0.71
    POSITIVE LOGITS
     partner
    0.97
     couples
    0.93
     monog
    0.91
     girlfriend
    0.89
    girlfriend
    0.89
    wife
    0.86
     boyfriend
    0.83
     marry
    0.83
     lia
    0.82
     partners
    0.82
    Activations Density 0.135%

    No Known Activations