© 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. 28063
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Summer" 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/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
    59
    +0.12
    0.7%
    112
    +0.12
    0.6%
    235
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.12
    0.02
    59
    +0.12
    0.01
    145
    +0.11
    0.02
    Negative Logits
     contaminated
    -1.71
     defective
    -1.63
     other
    -1.61
     imperfect
    -1.50
     exploiting
    -1.45
     interested
    -1.43
     corrupt
    -1.41
    aurus
    -1.41
     survived
    -1.40
     recovered
    -1.39
    POSITIVE LOGITS
    ¾
    2.39
    LY
    1.99
    finals
    1.98
    iversary
    1.96
    thur
    1.87
    strand
    1.84
     celebrations
    1.71
    belt
    1.71
    stroke
    1.70
    smen
    1.69
    Activations Density 0.078%

    No Known Activations