© 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. 1-RES-SM
    11. 28919
    Prev
    Next
    INDEX
    Explanations

    the indefinite article "um" and its variations in different 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    236
    +0.14
    0.8%
    111
    +0.12
    0.7%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.14
    0.01
    375
    +0.12
    0.01
    75
    +0.10
    0.01
    Negative Logits
    ings
    -1.80
    ments
    -1.72
    ctic
    -1.50
    ivities
    -1.50
    backs
    -1.47
    oretic
    -1.47
    resis
    -1.45
    ainen
    -1.42
     yourselves
    -1.39
     least
    -1.38
    POSITIVE LOGITS
    Īĺ
    2.35
    Ĭ
    2.29
    2.27
    ↵
    2.27
    2.27
    ↵  Âł
    2.27
    ↵
    2.27
    <|outofrange|>
    2.27
    ↵
    2.27
    2.27
    Activations Density 0.068%

    No Known Activations