© 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. 4-RES-SM
    11. 10819
    Prev
    Next
    INDEX
    Explanations

    contractions indicating future actions or plans

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.15
    0.9%
    410
    +0.14
    0.8%
    100
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.15
    0.08
    188
    +0.14
    0.04
    406
    +0.11
    0.06
    Negative Logits
    Ĥ
    -3.55
    ¿
    -3.45
    Ħ
    -3.41
    ¯
    -3.40
    °
    -3.37
    ¾
    -3.25
    -3.23
    -3.23
    -3.23
    -3.23
    POSITIVE LOGITS
     likely
    2.39
     want
    2.38
     notice
    2.33
     appreciate
    2.27
     find
    2.26
     need
    2.23
     lose
    2.23
     see
    2.22
     encounter
    2.21
     hear
    2.19
    Activations Density 0.462%

    No Known Activations