© 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. 30960
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software development and programming interfaces

    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
    263
    +0.15
    0.9%
    261
    +0.15
    0.8%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.15
    0.04
    325
    +0.15
    0.06
    450
    +0.14
    0.05
    Negative Logits
    ifice
    -1.57
     nevertheless
    -1.46
    uously
    -1.45
     nonetheless
    -1.42
    )].
    -1.41
    )],
    -1.41
    etically
    -1.40
     overall
    -1.39
     [[*
    -1.37
    iously
    -1.34
    POSITIVE LOGITS
    ŀ
    4.85
    Ĥ
    4.79
    ¦
    4.70
    ĨĴ
    4.59
    ·¸
    4.57
    ĥ½
    4.46
    Ĥ¬
    4.43
    ł
    4.39
    Ĩ
    4.38
    ª
    4.33
    Activations Density 0.347%

    No Known Activations