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. 7460
    Prev
    Next
    INDEX
    Explanations

    mentions of "love and friendship" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts, indicating connections between ideas or entities

    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
    •layer 8 - love

    No Comments

    Negative Logits
    Publisher
    -0.71
    *:
    -0.66
     Unch
    -0.64
     Pact
    -0.64
    :]
    -0.64
    Choice
    -0.64
     Zup
    -0.64
    £ı
    -0.63
    cens
    -0.61
     LEVEL
    -0.61
    POSITIVE LOGITS
     mortar
    0.75
    reen
    0.70
     pains
    0.68
     parenting
    0.68
    uries
    0.66
     wellness
    0.66
     nurturing
    0.66
    enf
    0.65
     grooming
    0.64
     heals
    0.64
    Activations Density 0.187%

    No Known Activations