© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    references to parallel execution 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
    156
    +0.15
    0.8%
    382
    +0.11
    0.6%
    387
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.15
    0.01
    325
    +0.11
    0.01
    80
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.53
    ľĵ
    -2.19
    ģ
    -2.02
    Ĥ¬
    -1.85
    ĻĤ
    -1.77
    ĵ
    -1.75
    thel
    -1.68
    fulness
    -1.66
    Ģ
    -1.63
    «
    -1.60
    POSITIVE LOGITS
     thereto
    1.94
     manner
    1.81
     ones
    1.78
    ism
    1.76
    ially
    1.74
    itely
    1.72
    ities
    1.69
     directions
    1.66
    osto
    1.64
    isations
    1.63
    Activations Density 0.126%

    No Known Activations