© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8938
    Prev
    Next
    INDEX
    Explanations

    topics related to media preservation and history

    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
    21
    +0.12
    0.7%
    491
    +0.12
    0.7%
    132
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.01
    221
    +0.12
    0.02
    491
    +0.10
    0.02
    Negative Logits
    gered
    -1.75
    igos
    -1.54
    acker
    -1.54
     favor
    -1.51
    urized
    -1.44
    ço
    -1.42
    icillin
    -1.38
    ester
    -1.35
    atile
    -1.34
     tool
    -1.32
    POSITIVE LOGITS
    References
    3.22
    Bibliography
    2.61
    Category
    2.38
    External
    2.32
    See
    2.25
    Notable
    2.17
    Notes
    2.07
    |-
    2.05
    Sources
    2.01
    disambiguation
    1.92
    Activations Density 0.066%

    No Known Activations