© 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. 28060
    Prev
    Next
    INDEX
    Explanations

    terms associated with physical and digital protection or security

    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
    148
    +0.12
    0.7%
    488
    +0.12
    0.6%
    162
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.12
    0.02
    148
    +0.12
    0.02
    378
    +0.11
    0.03
    Negative Logits
    ĨĴ
    -2.38
    Ĺ
    -2.11
    ĩ
    -2.00
    ¹
    -1.89
    ij
    -1.86
    »¿
    -1.85
    ª
    -1.81
    ¢
    -1.78
    Ķ
    -1.77
    ĥ
    -1.76
    POSITIVE LOGITS
    irector
    1.69
    rifug
    1.62
     credentials
    1.60
    efined
    1.57
    ness
    1.55
    GTH
    1.53
    emetery
    1.52
    etect
    1.51
     residues
    1.50
     behalf
    1.46
    Activations Density 0.190%

    No Known Activations