© 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. 2-RES-SM
    11. 26922
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to software or digital systems

    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
    153
    +0.21
    1.2%
    329
    +0.12
    0.7%
    323
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.21
    0.09
    329
    +0.12
    0.06
    323
    +0.12
    0.04
    Negative Logits
    onian
    -1.52
     whom
    -1.51
     reviewer
    -1.45
     whose
    -1.41
     trends
    -1.40
     husband
    -1.37
     personalities
    -1.36
     excel
    -1.36
     tendencies
    -1.34
     myself
    -1.33
    POSITIVE LOGITS
     ensued
    1.77
    ickets
    1.52
    fte
    1.46
    rails
    1.34
    rin
    1.32
    pin
    1.31
    orse
    1.30
    ipers
    1.30
    ime
    1.29
     lasted
    1.29
    Activations Density 3.106%

    No Known Activations