© 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. 4-RES-SM
    11. 15245
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or categories related to products or items 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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    309
    +0.14
    0.8%
    287
    +0.13
    0.7%
    88
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.14
    0.00
    172
    +0.13
    0.06
    88
    +0.12
    0.02
    Negative Logits
     nat
    -1.76
     NAT
    -1.52
    áĥĶ
    -1.52
     Echo
    -1.49
     Son
    -1.45
     PEG
    -1.45
     Wes
    -1.41
    ি
    -1.41
     waveguide
    -1.40
     echocardi
    -1.39
    POSITIVE LOGITS
     Cr
    3.42
    Cr
    2.78
    cr
    2.61
    ¿½
    2.59
     crater
    2.34
     Crus
    2.28
     cr
    2.27
     CR
    2.23
    ¥
    2.18
    ĩ
    2.09
    Activations Density 1.377%

    No Known Activations