© 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. 10237
    Prev
    Next
    INDEX
    Explanations

    mentions of arrays in programming 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
    156
    +0.22
    1.3%
    41
    +0.15
    0.8%
    301
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.22
    0.03
    272
    +0.15
    0.02
    420
    +0.12
    0.02
    Negative Logits
    chers
    -1.84
    cher
    -1.80
    ĵ
    -1.48
    ĥ½
    -1.48
    ------
    -1.45
    §
    -1.41
     progeny
    -1.41
    inine
    -1.39
    ^--
    -1.38
    employment
    -1.38
    POSITIVE LOGITS
    aterial
    1.69
    borne
    1.67
    WARE
    1.51
    plit
    1.51
    umbo
    1.49
    bie
    1.45
     transducer
    1.40
    onder
    1.39
    borg
    1.38
     props
    1.35
    Activations Density 0.063%

    No Known Activations