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

    Neuronpedia

    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. 2-RES-SM
    11. 28446
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Pennsylvania

    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/2-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.2.hook_resid_post
    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
    164
    +0.18
    1.1%
    369
    +0.16
    0.9%
    156
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.18
    0.03
    350
    +0.16
    0.03
    369
    +0.16
    0.01
    Negative Logits
    ĥ½
    -2.70
    ¼
    -2.62
    ½
    -2.38
    ľĵ
    -2.22
    £
    -2.11
    Īĺ
    -2.00
    tons
    -1.99
    »
    -1.97
    º
    -1.92
    ®
    -1.90
    POSITIVE LOGITS
    wn
    1.90
    hurst
    1.79
    quette
    1.70
    rst
    1.61
    ty
    1.59
    ulence
    1.58
    rice
    1.58
    ellar
    1.56
    kn
    1.54
    xy
    1.53
    Activations Density 0.155%

    No Known Activations