© 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. 14665
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the acquisition of knowledge or skills

    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
    307
    +0.18
    1.0%
    306
    +0.17
    1.0%
    383
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.18
    0.05
    472
    +0.17
    0.03
    406
    +0.13
    0.03
    Negative Logits
     backdrop
    -1.74
    Decided
    -1.73
    forth
    -1.70
    ilee
    -1.69
    amethasone
    -1.57
    ubicin
    -1.54
    illon
    -1.42
    ]>
    -1.42
    hea
    -1.42
    heed
    -1.41
    POSITIVE LOGITS
     about
    2.63
     how
    2.52
     lessons
    2.36
     lesson
    2.17
     anatomy
    2.14
    how
    2.07
     skills
    1.87
     new
    1.86
     strategies
    1.85
     math
    1.79
    Activations Density 0.445%

    No Known Activations