© 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. 12787
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    72
    +0.13
    0.7%
    507
    +0.13
    0.7%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.13
    0.07
    323
    +0.13
    0.03
    72
    +0.12
    0.04
    Negative Logits
    ↵
    -3.27
    ↵↵
    -3.27
    ↵
    -3.27
    ↵
    -3.27
    ↵↵
    -3.27
    ↵
    -3.27
     ↵
    -3.27
    ↵  ³³³
    -3.27
    -3.27
    ↵
    -3.27
    POSITIVE LOGITS
    enna
    1.70
     asleep
    1.60
    ESULT
    1.53
    _."
    1.47
    agra
    1.45
    TRODUCTION
    1.41
    onna
    1.41
    ethod
    1.40
    iceps
    1.39
    rror
    1.38
    Activations Density 1.020%

    No Known Activations