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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27550
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and electoral participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.21
    1.2%
    403
    +0.12
    0.7%
    125
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.21
    0.02
    358
    +0.12
    0.01
    125
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.80
    ·
    -2.65
    ©
    -2.41
    ĵ
    -2.34
    ľĵ
    -2.33
    Ŀ
    -2.24
    Ļª
    -2.21
    IJ
    -2.18
    ij
    -2.16
    ı
    -2.15
    POSITIVE LOGITS
    roup
    1.71
     styles
    1.67
     rights
    1.67
    cedure
    1.65
     ourselves
    1.54
    hell
    1.50
    stock
    1.49
    lass
    1.44
     yourself
    1.42
    cine
    1.38
    Activations Density 0.016%

    No Known Activations