© 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. 31861
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing information

    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
    186
    +0.12
    0.7%
    410
    +0.12
    0.7%
    333
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.12
    0.03
    453
    +0.12
    0.05
    109
    +0.12
    0.04
    Negative Logits
    ¯
    -3.11
    £
    -2.89
    -2.87
    ↵
    -2.87
    -2.87
    -2.87
    <|outofrange|>
    -2.87
    ↵
    -2.87
    č↵
    -2.87
    ↵↵
    -2.87
    POSITIVE LOGITS
    License
    1.76
     GNU
    1.74
     COPYRIGHT
    1.70
    TRODUCTION
    1.68
    ))$.
    1.66
     agreements
    1.66
     licenses
    1.64
     DISCLAIM
    1.64
     lic
    1.64
     NEGLIGENCE
    1.63
    Activations Density 0.889%

    No Known Activations