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

    Neuronpedia

    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. 2-RES-SM
    11. 30021
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present" used in a context suggesting current relevance or significance

    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
    335
    +0.14
    0.8%
    39
    +0.13
    0.7%
    381
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.02
    39
    +0.13
    0.01
    343
    +0.11
    0.01
    Negative Logits
    âĢŁ
    -1.61
     solids
    -1.55
    ichlet
    -1.53
     loyalty
    -1.45
     payable
    -1.41
     ++
    -1.35
     Bowl
    -1.31
     fines
    -1.30
     nullptr
    -1.29
    =".
    -1.29
    POSITIVE LOGITS
    ¨
    2.19
    ĸ
    2.19
    ī
    2.04
    ķ
    2.00
    ł
    1.98
    Ĥ
    1.97
    Ŀ
    1.88
     onwards
    1.81
    ¦
    1.81
    ence
    1.77
    Activations Density 0.033%

    No Known Activations