© 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. 10081
    Prev
    Next
    INDEX
    Explanations

    references to life stages and related themes

    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
    200
    +0.15
    0.9%
    406
    +0.14
    0.8%
    29
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.15
    0.03
    29
    +0.14
    0.01
    251
    +0.13
    0.02
    Negative Logits
    beit
    -1.86
    arthy
    -1.66
    issors
    -1.64
    ++)
    -1.57
    hib
    -1.57
     Asst
    -1.56
    ril
    -1.55
     large
    -1.54
    encil
    -1.51
     decir
    -1.47
    POSITIVE LOGITS
    Ģ
    2.97
    Ĭ
    2.69
    ¢
    2.65
    ·¸
    2.48
    ĥ½
    2.47
    ģ
    2.47
    Ħ
    2.41
    ĺ
    2.35
    ®
    2.35
    §
    2.33
    Activations Density 0.462%

    No Known Activations