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. 7473
    Prev
    Next
    INDEX
    Explanations

    phrases related to mourning or grief

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mourning and grief

    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
    •layer 8 - sadness

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.84
    urat
    -0.75
     Polo
    -0.71
    ouver
    -0.69
    onomy
    -0.69
    Testing
    -0.67
    efficients
    -0.67
    hibition
    -0.65
    uana
    -0.64
     retention
    -0.62
    POSITIVE LOGITS
     stricken
    0.82
     grieving
    0.81
    ously
    0.80
     widow
    0.80
     mourn
    0.80
    fully
    0.79
    ous
    0.77
     mourning
    0.76
     bere
    0.75
    mares
    0.74
    Activations Density 0.049%

    No Known Activations