© 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. 2-RES-SM
    11. 30731
    Prev
    Next
    INDEX
    Explanations

    instances of determiners and articles preceding nouns

    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
    501
    +0.16
    0.9%
    137
    +0.15
    0.8%
    75
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.16
    0.03
    137
    +0.15
    0.03
    8
    +0.13
    0.02
    Negative Logits
    fered
    -2.05
    omitempty
    -1.76
    hood
    -1.65
    igator
    -1.57
     flowed
    -1.52
    idian
    -1.48
     combining
    -1.46
     addition
    -1.43
    gery
    -1.43
     conducted
    -1.42
    POSITIVE LOGITS
    č↵
    6.42
        ↵
    6.42
    ↵↵
    6.42
    ↵
    6.42
    ↵
    6.42
                  ↵
    6.42
    6.42
    ↵↵
    6.42
    ↵↵
    6.42
      ↵
    6.42
    Activations Density 0.122%

    No Known Activations