© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1091
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, particularly sisters, in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "sister."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulkan
    -0.71
    ateurs
    -0.64
    beit
    -0.64
    imal
    -0.63
    vt
    -0.62
    urable
    -0.61
    holes
    -0.61
    animate
    -0.60
    ambo
    -0.60
    hematically
    -0.60
    POSITIVE LOGITS
     sister
    3.63
     sisters
    2.53
     brother
    2.39
     sibling
    2.30
     niece
    2.03
     cousin
    2.02
     Sister
    1.96
     daughter
    1.95
     siblings
    1.85
     aunt
    1.71
    Activations Density 0.007%

    No Known Activations