© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal involvement or collective 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
    240
    +0.15
    0.9%
    197
    +0.14
    0.8%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.15
    0.05
    206
    +0.14
    0.02
    455
    +0.13
    0.05
    Negative Logits
    illation
    -1.48
    fitting
    -1.45
     controversy
    -1.42
    iterator
    -1.41
    dating
    -1.36
     recognition
    -1.34
     secrecy
    -1.33
    matically
    -1.31
    °
    -1.27
     negot
    -1.25
    POSITIVE LOGITS
    itals
    1.44
    iscus
    1.43
    bour
    1.43
     fortunate
    1.42
    hs
    1.42
    strom
    1.41
    avian
    1.37
    Ca
    1.37
    imals
    1.37
    inia
    1.36
    Activations Density 0.817%

    No Known Activations