© 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. 28634
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions indicating frequency and occurrence

    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
    23
    +0.19
    1.1%
    363
    +0.13
    0.7%
    471
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.06
    83
    +0.13
    0.04
    471
    +0.13
    0.03
    Negative Logits
    ↵
    -4.27
    č↵
    -4.27
    ↵
    -4.27
    -4.27
     ↵
    -4.27
    -4.27
    -4.27
    -4.27
    <|outofrange|>
    -4.27
    č↵
    -4.27
    POSITIVE LOGITS
    kill
    2.02
    ugin
    1.80
    qu
    1.64
     prefer
    1.63
     nowadays
    1.62
    omnia
    1.59
     thereafter
    1.59
     som
    1.57
     tolerated
    1.56
     ever
    1.56
    Activations Density 0.551%

    No Known Activations