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. 8-RES-JB
    6. 19650
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and life events

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     takedown
    -0.91
    ibaba
    -0.84
    lethal
    -0.81
    XP
    -0.78
    weapons
    -0.75
     captcha
    -0.73
     stopp
    -0.72
    CVE
    -0.70
     sabotage
    -0.69
    tical
    -0.68
    POSITIVE LOGITS
     daughter
    1.42
     grandchildren
    1.39
     eldest
    1.37
     daughters
    1.36
     granddaughter
    1.33
     grandparents
    1.27
    husband
    1.23
     Wife
    1.22
     family
    1.19
     married
    1.18
    Activations Density 0.950%

    No Known Activations