© 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 EvalsExportsAPI 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. 26332
    Prev
    Next
    INDEX
    Explanations

    variations of the word "as" used 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
    424
    +0.17
    1.0%
    478
    +0.15
    0.9%
    221
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.17
    0.10
    502
    +0.15
    0.08
    41
    +0.13
    0.06
    Negative Logits
    ”)
    -1.57
    []
    -1.53
    UIT
    -1.52
    rive
    -1.47
    intage
    -1.46
    "];
    -1.44
    isites
    -1.43
    WS
    -1.43
    ish
    -1.41
    ISION
    -1.41
    POSITIVE LOGITS
    Ĥ
    3.09
    °
    3.04
    ¶
    2.94
    ı
    2.87
    ³
    2.85
    Īĺ
    2.82
    ī
    2.82
    ¼
    2.80
    ²
    2.72
    µ
    2.71
    Activations Density 0.255%

    No Known Activations