Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28928
    Prev
    Next
    INDEX
    Explanations

    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
    +0.17
    1.0%
    125
    +0.12
    0.7%
    400
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.17
    0.05
    402
    +0.12
    0.04
    480
    +0.11
    0.04
    Negative Logits
    Ī
    -2.36
    Ĩ
    -2.14
    ī
    -2.13
    ¤
    -2.03
    °
    -2.01
    »
    -1.99
    «
    -1.98
    ²
    -1.95
    ®
    -1.92
    ª
    -1.85
    POSITIVE LOGITS
     ways
    1.80
    orems
    1.77
     aforementioned
    1.68
     way
    1.68
     above
    1.66
     resources
    1.63
    rapeut
    1.62
    ogene
    1.61
    ses
    1.55
     steps
    1.54
    Activations Density 0.237%

    No Known Activations