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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18660
    Prev
    Next
    INDEX
    Explanations

    phrases related to political power structures, particularly oligarchies

    oai_token-act-pair · gpt-3.5-turbo

    references to oligarchs and their influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Robots
    -0.74
     Carolina
    -0.65
    erers
    -0.65
    head
    -0.62
     bras
    -0.62
    IL
    -0.61
    birth
    -0.60
    girl
    -0.60
     Robot
    -0.59
    ILS
    -0.59
    POSITIVE LOGITS
    eties
    1.05
    stan
    0.99
    etary
    0.92
    sis
    0.92
    sts
    0.88
    zed
    0.86
    arity
    0.84
    acy
    0.83
    sters
    0.82
    otomy
    0.82
    Activations Density 0.145%

    No Known Activations