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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23305
    Prev
    Next
    INDEX
    Explanations

    words related to grief or mourning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mourning and loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioch
    -0.80
    ãĥ³ãĤ¸
    -0.73
     Polo
    -0.71
    efficients
    -0.70
    entials
    -0.68
    oplan
    -0.68
    onomy
    -0.67
    uana
    -0.67
    Testing
    -0.64
    ouver
    -0.64
    POSITIVE LOGITS
     mourn
    0.97
     mourning
    0.84
     sorrow
    0.78
     grieving
    0.78
     bere
    0.75
     widow
    0.72
    DAQ
    0.71
     shroud
    0.70
    rieved
    0.69
     sadness
    0.69
    Activations Density 0.027%

    No Known Activations