© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29124
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or operational mechanisms

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.15
    0.9%
    189
    +0.14
    0.8%
    297
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.15
    0.02
    189
    +0.14
    0.01
    473
    +0.13
    0.01
    Negative Logits
    »¿
    -1.77
    ĥ½
    -1.66
     pound
    -1.61
     oath
    -1.57
     national
    -1.56
     vow
    -1.56
     taxpayer
    -1.53
     Letter
    -1.52
    urt
    -1.51
    ifax
    -1.51
    POSITIVE LOGITS
    wright
    1.77
    ics
    1.74
    aea
    1.63
    arily
    1.54
    grounds
    1.54
    ically
    1.52
    invariant
    1.52
     conserved
    1.51
    maker
    1.50
    idable
    1.48
    Activations Density 0.053%

    No Known Activations