© 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. 27156
    Prev
    Next
    INDEX
    Explanations

    legal terms and case citations

    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
    241
    +0.13
    0.7%
    153
    +0.12
    0.7%
    82
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.05
    232
    +0.12
    0.05
    185
    +0.11
    0.02
    Negative Logits
    izard
    -1.73
    hin
    -1.53
    ↵
    -1.50
    ander
    -1.50
    tes
    -1.49
     annealing
    -1.45
    obox
    -1.40
    ↵
    -1.38
    tm
    -1.35
    itum
    -1.34
    POSITIVE LOGITS
    Ĥ¬
    4.09
    ¦
    3.95
    ĨĴ
    3.87
    ģ
    3.86
    ¬
    3.83
    Ĭ
    3.83
    ŀ
    3.81
    ¿
    3.81
    Ī
    3.81
    Ļª
    3.80
    Activations Density 0.348%

    No Known Activations