© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26405
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational exchanges, often questioning or reflecting on personal interactions

    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
    287
    +0.17
    1.0%
    263
    +0.13
    0.7%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.17
    0.22
    243
    +0.13
    0.17
    500
    +0.12
    0.11
    Negative Logits
    ĻĤ
    -3.21
    ¾
    -2.31
    IJ
    -2.29
    ľĵ
    -2.24
    Ļª
    -2.10
    Ĺ
    -1.96
    ģ
    -1.92
    Īĺ
    -1.92
    ĩ
    -1.91
    «
    -1.88
    POSITIVE LOGITS
    )|$(
    1.50
    ко
    1.43
    ]."
    1.43
     Factory
    1.35
    icial
    1.32
    versible
    1.31
     flavour
    1.29
    issen
    1.23
    Äij
    1.21
    osite
    1.20
    Activations Density 6.738%

    No Known Activations