© 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. 26109
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence or existence in various contexts

    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
    24
    +0.14
    0.9%
    262
    +0.14
    0.8%
    126
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.09
    262
    +0.14
    0.06
    33
    +0.13
    0.09
    Negative Logits
    Ŀ
    -3.43
    ī
    -3.42
    ij
    -3.39
    Ĺ
    -3.35
    ĺ
    -3.33
    İ
    -3.33
    º
    -3.30
    Ĩ
    -3.29
    ĸ´
    -3.28
    ĥ
    -3.26
    POSITIVE LOGITS
    /~
    1.71
     """
    1.48
     /\
    1.45
     \%
    1.45
    RESULT
    1.40
    uto
    1.37
     urine
    1.31
    ------------------------------------------------------------------------
    1.30
     "</
    1.26
    tum
    1.23
    Activations Density 1.656%

    No Known Activations