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. 2-RES-JB
    6. 5102
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships with a focus on grandfathers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of grandfathers and grandparents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.93
    kell
    -0.76
    USE
    -0.74
    tics
    -0.74
    AAF
    -0.72
    coord
    -0.71
    election
    -0.69
    acus
    -0.67
    lez
    -0.67
    NEW
    -0.67
    POSITIVE LOGITS
     grandfather
    1.06
    father
    1.05
     Takeru
    0.89
     grandmother
    0.89
    parents
    0.89
     grandparents
    0.88
     aunt
    0.88
     patriarch
    0.84
     uncle
    0.83
     daddy
    0.82
    Activations Density 0.009%

    No Known Activations