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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3-RES-JB
    6. 22071
    Prev
    Next
    INDEX
    Explanations

    words related to philosophy and societal analysis

    oai_token-act-pair · gpt-3.5-turbo

    philosophical discussions about consciousness and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rollout
    -0.73
    Alert
    -0.64
    heast
    -0.63
     Pwr
    -0.62
     Sprint
    -0.60
    lbs
    -0.59
     Nationwide
    -0.59
     GoPro
    -0.59
     Tips
    -0.58
     Shutdown
    -0.57
    POSITIVE LOGITS
     epist
    0.91
     philosophers
    0.90
     Nietzsche
    0.85
     philosopher
    0.80
     Hegel
    0.79
     histor
    0.79
     poets
    0.77
     philosoph
    0.76
     oneself
    0.74
     metaphysical
    0.74
    Activations Density 3.000%

    No Known Activations