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. 15186
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly grandparents

    oai_token-act-pair · gpt-3.5-turbo

    references to grandparents

    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
    acus
    -0.76
    ylon
    -0.75
    okers
    -0.74
    jab
    -0.74
    rd
    -0.70
    urat
    -0.68
    ologne
    -0.67
    usal
    -0.67
    etheus
    -0.67
    obos
    -0.67
    POSITIVE LOGITS
    father
    0.97
    parents
    0.89
     grandmother
    0.88
     grandfather
    0.84
     grandma
    0.82
     Takeru
    0.82
    mother
    0.81
     grandparents
    0.80
     aunt
    0.78
     daddy
    0.77
    Activations Density 0.021%

    No Known Activations