© 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. 4-RES-SM
    11. 10327
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to interpersonal or diplomatic relationships

    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
    403
    +0.14
    0.8%
    149
    +0.12
    0.6%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.14
    0.06
    403
    +0.12
    0.03
    373
    +0.11
    0.05
    Negative Logits
    ½
    -4.55
    ¾
    -4.52
    ¿
    -4.52
    »¿
    -4.42
    ¼
    -4.39
    Ń
    -4.34
    ķ
    -4.31
    -4.30
    ↵
    -4.30
    -4.30
    POSITIVE LOGITS
     between
    4.76
    between
    3.59
     Between
    3.36
    hips
    2.96
     with
    2.67
     among
    2.42
     entre
    2.18
     amongst
    2.17
     involving
    2.16
     separating
    2.08
    Activations Density 0.594%

    No Known Activations