© 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. 12554
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements of existence or being

    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
    23
    +0.23
    1.4%
    233
    +0.16
    1.0%
    478
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.07
    103
    +0.16
    0.05
    289
    +0.15
    0.03
    Negative Logits
    »¿
    -2.44
    ł
    -2.23
    Ļª
    -2.19
      ↵
    -2.15
    -2.14
    č↵
    -2.14
    <|outofrange|>
    -2.14
    -2.14
    -2.14
    ↵↵
    -2.14
    POSITIVE LOGITS
     GPL
    1.94
     harmless
    1.72
     advised
    1.72
     equivalent
    1.62
     hereby
    1.62
     DEN
    1.61
     reversible
    1.61
     derivative
    1.58
     confidential
    1.58
     flag
    1.57
    Activations Density 0.381%

    No Known Activations