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. 22230
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal struggles and family issues, as well as actions such as sharing and volunteering

    oai_token-act-pair · gpt-3.5-turbo

    references to personal challenges and relationships, particularly surrounding infertility

    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
    £ı
    -0.77
    âĦ¢:
    -0.66
    buster
    -0.64
    osphere
    -0.62
     empir
    -0.61
    defense
    -0.60
    busters
    -0.59
     infographic
    -0.58
    Vote
    -0.58
     takedown
    -0.56
    POSITIVE LOGITS
     nurses
    0.78
     classmates
    0.77
     boyfriend
    0.76
     Nursing
    0.74
     babys
    0.74
     nursing
    0.72
     girlfriends
    0.72
     childhood
    0.72
     strangers
    0.71
     pregnancies
    0.71
    Activations Density 2.093%

    No Known Activations