© 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. 28159
    Prev
    Next
    INDEX
    Explanations

    the presence of periods indicating sentence endings

    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
    266
    +0.13
    0.7%
    249
    +0.12
    0.6%
    56
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.02
    271
    +0.12
    0.01
    156
    +0.11
    0.01
    Negative Logits
     ”
    -1.81
    ampl
    -1.71
     ’
    -1.57
     favor
    -1.51
     budget
    -1.51
    argo
    -1.51
    esto
    -1.48
    Ĩ
    -1.44
     salary
    -1.43
    rist
    -1.40
    POSITIVE LOGITS
    80211
    1.96
     namespace
    1.51
    Types
    1.46
    ictionaries
    1.45
    ITERATION
    1.44
     icons
    1.44
    illes
    1.41
     adaptations
    1.40
    ]--
    1.39
    WISE
    1.38
    Activations Density 0.004%

    No Known Activations