© 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. 2-RES-SM
    11. 9868
    Prev
    Next
    INDEX
    Explanations

    words associated with software licenses and copyright information

    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
    74
    +0.13
    0.7%
    145
    +0.12
    0.7%
    119
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.13
    0.02
    74
    +0.12
    0.01
    453
    +0.11
    0.02
    Negative Logits
    ľĵ
    -2.08
    ®
    -2.04
     wonder
    -1.86
    ugin
    -1.84
     same
    -1.79
    İ
    -1.66
     remember
    -1.56
    ł
    -1.55
    ı
    -1.52
    Ń
    -1.51
    POSITIVE LOGITS
     itself
    1.94
     Engineering
    1.57
     Intelligence
    1.55
    ician
    1.52
    ulence
    1.50
    ystems
    1.50
    ificial
    1.48
     Enforcement
    1.47
    iverse
    1.44
    ÑĤа
    1.43
    Activations Density 0.037%

    No Known Activations