Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9-RES-JB
    6. 4455
    Prev
    Next
    INDEX
    Explanations

    references to family members, including siblings and extended family

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.86
    ioxide
    -0.86
    asive
    -0.83
    Ĥİ
    -0.82
    IUM
    -0.81
    agnetic
    -0.81
    CAP
    -0.81
    etting
    -0.78
     Controlled
    -0.76
    vironment
    -0.76
    POSITIVE LOGITS
     sisters
    1.61
     nephew
    1.58
     siblings
    1.58
     grandparents
    1.57
     aunt
    1.57
     sister
    1.57
     cousins
    1.56
     grandmother
    1.55
     niece
    1.53
     brother
    1.50
    Activations Density 0.208%

    No Known Activations