© 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. 10442
    Prev
    Next
    INDEX
    Explanations

    discussions related to legislation and government actions

    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
    104
    +0.14
    0.8%
    344
    +0.13
    0.7%
    364
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.14
    0.14
    178
    +0.13
    0.09
    104
    +0.12
    0.02
    Negative Logits
     arte
    -2.13
    Ł
    -2.08
     fibres
    -2.06
    -1.94
    ↵
    -1.94
    ↵↵
    -1.94
    ↵
    -1.94
    -1.94
    <|outofrange|>
    -1.94
     ↵
    -1.94
    POSITIVE LOGITS
     bipartisan
    4.03
     lawmakers
    3.98
     Senate
    3.90
     Republicans
    3.73
     legislative
    3.62
     legislators
    3.62
     Democrats
    3.58
     repeal
    3.56
     congressional
    3.48
     GOP
    3.38
    Activations Density 3.640%

    No Known Activations