© 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. 13296
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you" 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/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
    +0.13
    0.8%
    21
    +0.12
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.13
    0.10
    363
    +0.12
    0.08
    162
    +0.12
    0.05
    Negative Logits
    ĻĤ
    -2.08
    ¶
    -1.98
    ij
    -1.82
    Ħ
    -1.82
    »¿
    -1.81
    ¤
    -1.81
    ĺ
    -1.78
    ľ
    -1.77
    IED
    -1.72
    iary
    -1.70
    POSITIVE LOGITS
    're
    3.40
     want
    2.71
    'll
    2.50
     wish
    2.49
    've
    2.47
    want
    2.47
     intend
    2.34
     are
    2.19
     choose
    2.15
     need
    2.10
    Activations Density 0.440%

    No Known Activations