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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2293
    Prev
    Next
    INDEX
    Explanations

    mentions of friends and family in social contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to friends and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.76
    oliberal
    -0.71
    ãĥ¯ãĥ³
    -0.68
    ãĥķãĤ©
    -0.68
    ï¸
    -0.67
     gears
    -0.66
    Ops
    -0.66
     pollut
    -0.65
    ãĤ¢ãĥ«
    -0.64
    ãĥ¼ãĥ«
    -0.63
    POSITIVE LOGITS
     neighbours
    0.85
     coworkers
    0.84
     neighbors
    0.83
    mates
    0.83
     sibling
    0.83
     whom
    0.80
     acquaintances
    0.79
     relatives
    0.79
     siblings
    0.78
    ioch
    0.75
    Activations Density 0.385%

    No Known Activations