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. 3236
    Prev
    Next
    INDEX
    Explanations

    words related to specific ideologies or philosophical concepts, particularly those with an -ian or -ism suffix

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix "-ian" or similar

    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
    Downloadha
    -1.19
    drops
    -0.90
    pots
    -0.89
    bsite
    -0.86
    click
    -0.84
    pot
    -0.82
    lehem
    -0.80
    matched
    -0.79
    liga
    -0.79
    isSpecialOrderable
    -0.79
    POSITIVE LOGITS
     Era
    0.96
     Revival
    0.96
     ancestors
    0.88
     heritage
    0.88
     era
    0.86
     Orthodox
    0.85
     worldview
    0.83
     ancestor
    0.82
     hegemony
    0.82
     grandmother
    0.82
    Activations Density 0.141%

    No Known Activations