© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    phrases related to temporal and possessive relationships

    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
    +0.18
    1.0%
    364
    +0.13
    0.7%
    43
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.18
    0.01
    238
    +0.13
    0.04
    136
    +0.12
    -0.01
    Negative Logits
    chers
    -1.63
     similarities
    -1.59
     implications
    -1.50
     surrounds
    -1.48
     biases
    -1.44
     faces
    -1.41
     credentials
    -1.41
     tastes
    -1.40
     angles
    -1.40
     stains
    -1.39
    POSITIVE LOGITS
    2.09
                  ↵
    2.09
    ↵
    2.09
    č↵
    2.09
    ↵
    2.09
    ↵
    2.09
     ↵
    2.09
    2.09
    2.09
    ↵↵
    2.09
    Activations Density 0.463%

    No Known Activations