© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 11226
    Prev
    Next
    INDEX
    Explanations

    punctuation specifically in the form of commas

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    391
    +0.12
    0.7%
    294
    +0.12
    0.7%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.12
    0.03
    74
    +0.12
    0.02
    294
    +0.12
    0.02
    Negative Logits
     parl
    -1.55
    blogger
    -1.50
     campaigns
    -1.41
     conversions
    -1.40
    riber
    -1.38
    .[]{
    -1.38
    []{
    -1.38
     lately
    -1.37
     mine
    -1.36
    cele
    -1.34
    POSITIVE LOGITS
    sible
    1.53
     arbitrarily
    1.35
    sein
    1.30
     knowing
    1.27
     discontin
    1.27
    pers
    1.25
    iness
    1.25
     @"
    1.20
    ius
    1.20
     sua
    1.19
    Activations Density 0.075%

    No Known Activations