© 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. 26343
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Alexander."

    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
    156
    +0.15
    0.9%
    508
    +0.12
    0.7%
    51
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.15
    0.03
    73
    +0.12
    0.02
    327
    +0.12
    0.03
    Negative Logits
    ieurs
    -1.89
    ercase
    -1.81
    ière
    -1.63
    isión
    -1.57
    ository
    -1.54
    eren
    -1.53
    lich
    -1.49
     recent
    -1.49
    lop
    -1.48
    >",
    -1.39
    POSITIVE LOGITS
    ŀ
    2.68
    Ľ
    2.39
    Ŀ
    2.35
    ĸ
    2.32
    Į
    2.23
    ¢
    2.13
    £
    2.12
    ¤
    2.06
    ¾
    2.05
    İ
    2.02
    Activations Density 0.274%

    No Known Activations