© 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. 10128
    Prev
    Next
    INDEX
    Explanations

    references to data size and complexity in scientific 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/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
    350
    +0.13
    0.7%
    187
    +0.12
    0.6%
    29
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.04
    102
    +0.12
    0.05
    187
    +0.11
    0.04
    Negative Logits
    etine
    -1.65
    ecause
    -1.59
    ilde
    -1.51
    obbsee
    -1.47
    Ñĥн
    -1.45
     same
    -1.43
     direction
    -1.41
    occ
    -1.41
    ETHOD
    -1.39
    rile
    -1.39
    POSITIVE LOGITS
     amounts
    3.08
     enough
    2.49
     amount
    2.43
     quantities
    2.42
     (\>
    2.40
     sized
    2.38
     sums
    2.30
     number
    2.28
     numbers
    2.25
     (>
    2.15
    Activations Density 0.138%

    No Known Activations