© 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. 26145
    Prev
    Next
    INDEX
    Explanations

    terms related to biological mechanisms and processes

    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
    5
    +0.12
    0.7%
    356
    +0.12
    0.6%
    389
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.12
    0.02
    306
    +0.12
    0.01
    287
    +0.11
    0.02
    Negative Logits
    »¿
    -2.29
    ĻĤ
    -2.19
    ĥ½
    -2.07
    ľĵ
    -2.01
    §
    -1.91
    «
    -1.84
    Â
    -1.82
    <|outofrange|>
    -1.82
    -1.82
                  ↵
    -1.82
    POSITIVE LOGITS
     responsible
    1.88
     whereby
    1.82
     underlying
    1.64
    idable
    1.58
     conserved
    1.58
     operative
    1.54
     triggering
    1.53
     enrichment
    1.53
    atics
    1.53
    coupling
    1.50
    Activations Density 0.089%

    No Known Activations