© 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. 2-RES-SM
    11. 10531
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical levels or rankings in various 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/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
    164
    +0.15
    0.9%
    500
    +0.14
    0.8%
    172
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.15
    0.03
    172
    +0.14
    0.03
    500
    +0.13
    0.03
    Negative Logits
    ĻĤ
    -2.75
    ľĵ
    -2.43
    ¥
    -2.24
    ¦
    -2.20
    ½
    -2.15
    ĸ
    -2.12
    ¢
    -2.08
    IJ
    -2.05
    ĨĴ
    -2.01
    ²
    -2.00
    POSITIVE LOGITS
    ups
    1.80
    way
    1.74
    offs
    1.72
     ranges
    1.71
     thresholds
    1.66
    ahead
    1.66
     crossings
    1.64
    points
    1.64
     varies
    1.63
    imetric
    1.63
    Activations Density 0.100%

    No Known Activations