© 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. 4-RES-SM
    11. 12717
    Prev
    Next
    INDEX
    Explanations

    references to modernity and contemporary themes

    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
    +0.17
    1.0%
    112
    +0.12
    0.7%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.17
    0.04
    326
    +0.12
    0.04
    424
    +0.12
    0.03
    Negative Logits
     particular
    -1.70
     0000000000000000000000000000000000
    -1.58
     Pradesh
    -1.55
     evenly
    -1.51
    particular
    -1.51
     cref
    -1.47
    igate
    -1.47
    лем
    -1.44
     specific
    -1.42
    ancia
    -1.41
    POSITIVE LOGITS
    £
    2.77
    µ
    2.67
    ized
    2.60
    °
    2.56
    ł
    2.47
    ¾
    2.47
    izing
    2.35
    ´
    2.29
    ised
    2.26
    izers
    2.21
    Activations Density 0.320%

    No Known Activations