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. 6-RES-JB
    6. 8387
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive determiners referring to relationships between family members

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and parental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strikes
    -0.86
    Rank
    -0.81
    Combat
    -0.80
    rank
    -0.73
    Quant
    -0.72
    weapons
    -0.70
    CHQ
    -0.68
    furt
    -0.68
     feats
    -0.68
    Course
    -0.68
    POSITIVE LOGITS
     daughter
    1.01
     Daughter
    0.97
     granddaughter
    0.96
     patriarch
    0.94
     grandchildren
    0.94
    husband
    0.93
     grandson
    0.91
     husband
    0.91
     divorced
    0.90
     son
    0.88
    Activations Density 0.443%

    No Known Activations