© 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. 27753
    Prev
    Next
    INDEX
    Explanations

    references to quantities of material, particularly in terms of tons and other weight measurements

    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
    94
    +0.13
    0.7%
    182
    +0.13
    0.7%
    286
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.05
    156
    +0.13
    0.04
    182
    +0.12
    0.03
    Negative Logits
    ETHOD
    -1.73
    áĢº
    -1.53
    rely
    -1.52
    áĢ¯
    -1.51
    atore
    -1.50
     counsel
    -1.50
     victim
    -1.48
    ANNEL
    -1.41
     coding
    -1.41
     sender
    -1.41
    POSITIVE LOGITS
    ioned
    2.02
    elled
    1.96
    Ģ
    1.71
    »¿
    1.64
    ume
    1.62
    °
    1.59
    ahead
    1.57
    ylon
    1.57
    imet
    1.55
    ified
    1.50
    Activations Density 0.350%

    No Known Activations