© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    comparative phrases suggesting a quantity or degree

    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
    510
    +0.12
    0.7%
    383
    +0.11
    0.6%
    499
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.12
    0.04
    383
    +0.11
    0.04
    284
    +0.10
    0.04
    Negative Logits
    IJ
    -2.48
    Īĺ
    -2.42
    ĸ
    -2.42
    ¦
    -2.40
    ij
    -2.36
    ¿½
    -2.30
    Ĺ
    -2.29
    ģ
    -2.27
    ĻĤ
    -2.24
    ľĵ
    -2.23
    POSITIVE LOGITS
     anybody
    1.48
    irection
    1.47
    ness
    1.46
     additive
    1.41
     slightest
    1.40
    cule
    1.39
    ferentially
    1.37
    gaard
    1.36
    driving
    1.34
    rous
    1.33
    Activations Density 0.167%

    No Known Activations