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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11344
    Prev
    Next
    INDEX
    Explanations

    the use of the word "to" 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
    336
    +0.15
    0.8%
    150
    +0.11
    0.6%
    95
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.15
    0.06
    336
    +0.11
    0.07
    95
    +0.11
    0.06
    Negative Logits
     choices
    -1.61
     mistakes
    -1.59
     Facts
    -1.53
     deeds
    -1.53
    ings
    -1.52
     factors
    -1.50
     clues
    -1.48
     bullet
    -1.47
    INGS
    -1.45
     rider
    -1.40
    POSITIVE LOGITS
    ither
    1.85
    ugu
    1.77
    ipel
    1.74
    inai
    1.73
    ctic
    1.68
    xico
    1.68
     occupied
    1.56
    googleapis
    1.51
    home
    1.50
     rented
    1.48
    Activations Density 1.051%

    No Known Activations