© 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. 30997
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotional expressions

    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
    419
    +0.23
    1.3%
    483
    +0.14
    0.8%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.23
    0.04
    502
    +0.14
    0.04
    483
    +0.12
    0.05
    Negative Logits
    Ļª
    -3.18
    ¸
    -2.57
    ĭ
    -2.38
    ij
    -2.34
    ĺ
    -2.30
    ¼
    -2.30
    ĻĤ
    -2.29
    °
    -2.28
    ©
    -2.27
    Ģ
    -2.27
    POSITIVE LOGITS
     won
    1.89
    č↵
    1.49
    ophageal
    1.37
     latter
    1.37
    ás
    1.36
     tou
    1.35
     caso
    1.32
     nested
    1.32
     sporadic
    1.31
     iter
    1.30
    Activations Density 0.345%

    No Known Activations