© 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. 4-RES-SM
    11. 13839
    Prev
    Next
    INDEX
    Explanations

    information related to creative works and artistic expression

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    466
    +0.16
    1.1%
    25
    +0.12
    0.8%
    334
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.16
    0.14
    122
    +0.12
    0.10
    510
    +0.11
    0.13
    Negative Logits
    ĻĤ
    -5.92
    Ģ
    -5.84
    Ī
    -5.74
    Ł
    -5.66
    ĨĴ
    -5.66
       ↵
    -5.63
     ↵
    -5.63
    ↵
    -5.63
    ↵
    -5.63
    -5.63
    POSITIVE LOGITS
     respectively
    1.90
     their
    1.86
     theirs
    1.74
    thems
    1.60
    their
    1.56
    .[@
    1.56
     Their
    1.54
     ever
    1.50
    .|
    1.48
     thereto
    1.46
    Activations Density 2.238%

    No Known Activations