© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13850
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and their electoral prospects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.33
    1.9%
    306
    +0.23
    1.3%
    287
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.33
    0.18
    306
    +0.23
    0.11
    447
    +0.15
    0.12
    Negative Logits
     dragons
    -1.67
     irradiation
    -1.64
     Dragon
    -1.60
     Imperial
    -1.58
    ubicin
    -1.56
     radiotherapy
    -1.55
     AML
    -1.55
     armour
    -1.54
     ÅŁi
    -1.53
     Ukraine
    -1.53
    POSITIVE LOGITS
    ĻĤ
    2.93
    ¿½
    2.58
    ¬
    2.33
       ↵
    2.33
    ↵↵
    2.33
    2.33
     ↵
    2.33
    2.33
    <|outofrange|>
    2.33
    ↵
    2.33
    Activations Density 2.631%

    No Known Activations