© 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. 31667
    Prev
    Next
    INDEX
    Explanations

    words related to names or identity

    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
    256
    +0.14
    0.8%
    410
    +0.12
    0.7%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.14
    0.05
    59
    +0.12
    0.03
    410
    +0.12
    0.05
    Negative Logits
     validity
    -1.68
     receiver
    -1.62
    xygen
    -1.62
    ensure
    -1.44
     magnitude
    -1.40
     United
    -1.35
     intolerance
    -1.34
    cribing
    -1.27
    ortic
    -1.26
     receivers
    -1.26
    POSITIVE LOGITS
    inja
    1.85
    ikov
    1.80
    andez
    1.79
    stein
    1.76
    ostics
    1.74
    dez
    1.69
    astic
    1.68
    quist
    1.66
    amed
    1.65
    iveau
    1.62
    Activations Density 0.402%

    No Known Activations