© 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 EvalsExportsAPI 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. 27669
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities related to people or organizations

    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
    369
    +0.23
    1.3%
    59
    +0.15
    0.9%
    191
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.23
    0.03
    369
    +0.15
    0.03
    191
    +0.10
    0.02
    Negative Logits
    actic
    -1.70
    ky
    -1.61
    lasses
    -1.56
     throat
    -1.54
     Parenthood
    -1.49
     ear
    -1.48
     footsteps
    -1.47
     becoming
    -1.47
     curative
    -1.41
    dn
    -1.40
    POSITIVE LOGITS
    leys
    2.00
    wey
    1.90
    legate
    1.78
     facto
    1.65
    le
    1.65
    emos
    1.56
    ijo
    1.56
    velope
    1.54
    bbie
    1.52
    hal
    1.51
    Activations Density 0.067%

    No Known Activations