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. 1-RES-JB
    6. 14946
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, specifically nephews and nieces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of family relationships, particularly those involving 'nephew' and 'niece'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.84
    ffen
    -0.73
    utterstock
    -0.70
    uter
    -0.69
     iod
    -0.66
     whales
    -0.66
    âĸ¬âĸ¬
    -0.63
    enges
    -0.63
    metal
    -0.63
    =~=~
    -0.63
    POSITIVE LOGITS
    sworth
    0.84
     niece
    0.83
    iosyncr
    0.82
    lique
    0.82
    rift
    0.81
    romeda
    0.80
    paralle
    0.79
    LY
    0.77
    lies
    0.77
    sy
    0.75
    Activations Density 0.022%

    No Known Activations