© 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 EvalsExportsinterp-engineNEWAPI 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. 14156
    Prev
    Next
    INDEX
    Explanations

    operational verbs in various contexts

    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
    21
    +0.12
    0.6%
    41
    +0.11
    0.6%
    218
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.12
    0.03
    41
    +0.11
    0.02
    120
    +0.11
    0.03
    Negative Logits
     respect
    -1.80
    ize
    -1.67
     chance
    -1.59
    vity
    -1.54
     favour
    -1.52
     due
    -1.52
    IFF
    -1.51
    thur
    -1.47
     favor
    -1.46
    CCESS
    -1.46
    POSITIVE LOGITS
    hthal
    2.35
    edia
    2.04
    aque
    1.99
    ulmonary
    1.93
    ilot
    1.90
    aminergic
    1.86
    onent
    1.84
    reserved
    1.76
    ération
    1.75
    olis
    1.71
    Activations Density 0.110%

    No Known Activations