© 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. 28428
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive pronouns associated with personal experiences

    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
    161
    +0.13
    0.7%
    93
    +0.12
    0.6%
    219
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.13
    0.08
    250
    +0.12
    0.09
    81
    +0.11
    0.07
    Negative Logits
    ĻĤ
    -5.55
    -5.49
    -5.49
    ↵
    -5.49
    ↵
    -5.49
    ↵
    -5.49
    ↵
    -5.49
    ↵
    -5.49
    ↵            ↵
    -5.49
    ↵
    -5.49
    POSITIVE LOGITS
    protobuf
    1.41
    ulum
    1.37
     Saudi
    1.37
    cin
    1.37
    audi
    1.37
    bands
    1.33
     patented
    1.32
    vet
    1.32
     lobe
    1.32
    nen
    1.31
    Activations Density 0.562%

    No Known Activations