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. 10-RES-JB
    6. 8751
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies or movements, particularly those involving Islam

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -1.04
     anecd
    -0.89
     anecdotes
    -0.80
     anecdotal
    -0.76
    visors
    -0.73
     Advisory
    -0.72
     commenters
    -0.71
    comments
    -0.71
     Mermaid
    -0.70
     Volunte
    -0.70
    POSITIVE LOGITS
     hegemony
    1.33
     conquest
    1.27
     communism
    1.22
     domination
    1.22
     tyranny
    1.21
     revenge
    1.20
     jihad
    1.18
     Communism
    1.18
     overthrow
    1.16
     Islam
    1.15
    Activations Density 0.426%

    No Known Activations