© 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. 27158
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    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
    98
    +0.29
    1.7%
    291
    +0.15
    0.9%
    10
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.29
    0.08
    291
    +0.15
    0.09
    98
    +0.14
    0.03
    Negative Logits
    ãģ£ãģŁ
    -1.55
    "}](#
    -1.53
    eer
    -1.30
    ãģ³
    -1.28
    ια
    -1.28
    ptions
    -1.24
    cing
    -1.24
    imal
    -1.24
     slog
    -1.23
     ceil
    -1.23
    POSITIVE LOGITS
    »¿
    3.49
    ĨĴ
    2.87
    ĻĤ
    2.15
    2.12
    2.12
    ↵↵
    2.12
    2.12
    <|outofrange|>
    2.12
    ↵  Âł
    2.12
    č↵
    2.12
    Activations Density 0.501%

    No Known Activations