© 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. 32237
    Prev
    Next
    INDEX
    Explanations

    references to various forms of intervention and related therapeutic actions

    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
    156
    +0.18
    1.0%
    184
    +0.12
    0.7%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.18
    0.02
    177
    +0.12
    0.01
    344
    +0.12
    0.02
    Negative Logits
    »¿
    -2.16
     fortunate
    -1.88
    ĻĤ
    -1.86
     lucky
    -1.79
    ¿½
    -1.72
    ĥ½
    -1.67
     guilty
    -1.64
    chitz
    -1.63
    hurst
    -1.62
    croft
    -1.57
    POSITIVE LOGITS
    al
    2.11
     aimed
    1.92
    hoc
    1.75
     targeting
    1.68
    ally
    1.67
    aging
    1.61
    ISM
    1.58
    ism
    1.55
     applied
    1.54
    optional
    1.52
    Activations Density 0.107%

    No Known Activations