© 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. 11054
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness or readiness to take action or make decisions

    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
    258
    +0.17
    1.0%
    232
    +0.13
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.08
    450
    +0.13
    0.05
    258
    +0.12
    0.08
    Negative Logits
    etimes
    -1.74
    plasia
    -1.53
    ![**
    -1.48
    Suite
    -1.47
    rams
    -1.43
    itatively
    -1.43
     parl
    -1.40
    sets
    -1.40
    olor
    -1.39
    ram
    -1.38
    POSITIVE LOGITS
     submission
    1.86
     euthan
    1.68
     surrender
    1.68
    holds
    1.65
     resignation
    1.61
     relinqu
    1.61
     plea
    1.51
     withdrawing
    1.50
     reass
    1.50
     indemn
    1.48
    Activations Density 1.180%

    No Known Activations