© 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. 28880
    Prev
    Next
    INDEX
    Explanations

    structured data and layout configurations in coding or design contexts

    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
    +0.30
    1.7%
    507
    +0.15
    0.9%
    465
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.30
    0.07
    57
    +0.15
    0.02
    466
    +0.12
    0.02
    Negative Logits
    liga
    -1.82
    ferent
    -1.74
    anks
    -1.58
    ressor
    -1.57
    80211
    -1.57
    innen
    -1.55
     category
    -1.55
    liche
    -1.53
    velopment
    -1.52
    blic
    -1.51
    POSITIVE LOGITS
     mornings
    1.85
    woke
    1.75
    cted
    1.67
    inary
    1.61
     peaceful
    1.55
     evenings
    1.53
    enced
    1.45
    iy
    1.43
     Lat
    1.41
    ight
    1.40
    Activations Density 1.151%

    No Known Activations