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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5910
    Prev
    Next
    INDEX
    Explanations

    mention of family relationships, particularly between different relatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to family relationships and dynamics

    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
     guiName
    -0.80
     oneself
    -0.77
    dimensional
    -0.74
     quantify
    -0.67
     ourselves
    -0.66
    henko
    -0.66
    nergy
    -0.66
    legged
    -0.64
    idas
    -0.63
    youtu
    -0.62
    POSITIVE LOGITS
     hers
    0.76
    iHUD
    0.72
     theirs
    0.72
     disappro
    0.69
     jealous
    0.68
     tuberculosis
    0.68
    amily
    0.67
     nursing
    0.67
    ifi
    0.66
     NIC
    0.66
    Activations Density 0.426%

    No Known Activations