© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Al" in various 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
    369
    +0.23
    1.3%
    443
    +0.16
    0.9%
    2
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.23
    0.04
    97
    +0.16
    0.04
    369
    +0.14
    0.03
    Negative Logits
    atory
    -1.72
    disambiguation
    -1.51
    CRIPT
    -1.43
    ABLE
    -1.41
    cha
    -1.37
    IRST
    -1.35
    forth
    -1.35
    ALSE
    -1.34
    idyl
    -1.34
    IRS
    -1.32
    POSITIVE LOGITS
    thouse
    2.21
    ison
    2.02
    veolar
    1.94
    leys
    1.91
    varez
    1.79
    phabet
    1.71
    ibaba
    1.66
    gorithms
    1.65
    onso
    1.64
    izar
    1.64
    Activations Density 0.198%

    No Known Activations