© 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. 4-RES-SM
    11. 9283
    Prev
    Next
    INDEX
    Explanations

    words or phrases that denote rarity or uniqueness

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.14
    0.8%
    118
    +0.13
    0.7%
    54
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.08
    137
    +0.13
    0.07
    118
    +0.12
    0.06
    Negative Logits
    à¸ĩ
    -1.63
    าà¸
    -1.47
    еÑĤе
    -1.46
    ahren
    -1.43
    anas
    -1.40
    ARS
    -1.39
    ั
    -1.38
    eks
    -1.37
    ILE
    -1.37
     públic
    -1.35
    POSITIVE LOGITS
    ¿½
    2.80
    ª
    2.80
    ľĵ
    2.76
    ®
    2.74
    ¾
    2.61
    ĥ
    2.61
    Ĵ
    2.60
    Ł
    2.56
    ĨĴ
    2.51
    ı
    2.50
    Activations Density 0.701%

    No Known Activations