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. 19525
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly those involving in-laws

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships, particularly in a legal context

    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
    IUM
    -0.77
    ¶ħ
    -0.59
     contingency
    -0.57
     simul
    -0.55
     inspections
    -0.55
     qualifiers
    -0.55
     calibrated
    -0.55
     popcorn
    -0.54
     pressures
    -0.54
     surface
    -0.54
    POSITIVE LOGITS
    daughter
    0.92
    hood
    0.89
    wife
    0.89
    backer
    0.82
    brother
    0.82
    Allah
    0.76
    lege
    0.76
    son
    0.75
    band
    0.75
    girlfriend
    0.74
    Activations Density 0.102%

    No Known Activations