© 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 EvalsExportsinterp-engineNEWAPI 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. 13710
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "you."

    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
    369
    +0.17
    0.9%
    478
    +0.16
    0.9%
    159
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.17
    0.05
    159
    +0.16
    0.06
    41
    +0.13
    0.06
    Negative Logits
    °
    -4.95
    ļ
    -4.93
    Ħ
    -4.93
    ŀ
    -4.92
    ľ
    -4.82
    -4.75
    -4.75
    č↵
    -4.75
    <|outofrange|>
    -4.75
    -4.75
    POSITIVE LOGITS
    'll
    2.13
    're
    2.03
     guys
    2.02
     plead
    1.81
    've
    1.78
     want
    1.72
     wish
    1.71
    want
    1.69
    get
    1.69
    ply
    1.68
    Activations Density 0.198%

    No Known Activations