© 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. Residuals
    9. 4-RES-SM
    11. 12925
    Prev
    Next
    INDEX
    Explanations

    elements related to official processes or regulations in Michigan

    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
    280
    +0.13
    0.7%
    216
    +0.10
    0.6%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.13
    0.08
    105
    +0.10
    0.07
    258
    +0.10
    0.06
    Negative Logits
     Sri
    -2.99
     Dh
    -2.65
     Australians
    -2.23
     Adelaide
    -2.09
     programmes
    -2.09
     Bh
    -2.08
     Thai
    -2.07
     Bangladesh
    -2.04
     PNG
    -2.03
     behavioural
    -2.01
    POSITIVE LOGITS
     Ohio
    4.33
     Michigan
    4.33
    Ohio
    3.55
     Detroit
    3.51
    Mich
    3.46
     Cincinnati
    3.41
     Snyder
    3.37
     Wisconsin
    3.22
     Columbus
    3.20
     Buc
    3.07
    Activations Density 1.242%

    No Known Activations