© 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. 1-RES-SM
    11. 26311
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to processes and materials in a scientific or engineering context

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    2
    +0.11
    0.6%
    471
    +0.11
    0.6%
    321
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.11
    0.01
    321
    +0.11
    0.01
    177
    +0.10
    0.01
    Negative Logits
     else
    -1.76
    Ĥ¬
    -1.72
    doing
    -1.60
    catch
    -1.60
    ¹
    -1.53
    xico
    -1.51
    leans
    -1.50
    ĥ
    -1.49
    ĸ´
    -1.49
    LLOW
    -1.47
    POSITIVE LOGITS
    ulence
    2.29
    ulent
    2.03
    thouse
    1.87
    iev
    1.82
    imetric
    1.77
    imeter
    1.75
    ution
    1.74
    illo
    1.73
    itious
    1.67
    iban
    1.66
    Activations Density 0.055%

    No Known Activations