© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25288
    Prev
    Next
    INDEX
    Explanations

    mentions of the U.S. presidency and its related roles

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    485
    +0.12
    0.6%
    261
    +0.11
    0.6%
    99
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.03
    298
    +0.11
    0.03
    485
    +0.11
    0.02
    Negative Logits
     radio
    -1.44
    cgi
    -1.36
     radios
    -1.34
     clicking
    -1.33
     manners
    -1.31
    oused
    -1.31
    inho
    -1.29
     travellers
    -1.27
     confidentiality
    -1.26
     newspapers
    -1.26
    POSITIVE LOGITS
     Chan
    1.50
     envisioned
    1.46
     2021
    1.39
    annon
    1.38
    beth
    1.37
     conclude
    1.36
    ientos
    1.35
    }",
    1.35
     meaning
    1.32
    akh
    1.31
    Activations Density 0.138%

    No Known Activations