© 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. 2-RES-SM
    11. 26761
    Prev
    Next
    INDEX
    Explanations

    references to TV shows and their cultural impact

    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
    479
    +0.17
    1.0%
    141
    +0.14
    0.8%
    263
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.17
    0.08
    141
    +0.14
    0.08
    293
    +0.14
    0.11
    Negative Logits
     herself
    -1.75
    »¿
    -1.49
    minist
    -1.47
    inated
    -1.46
     Asst
    -1.45
    ém
    -1.43
    istically
    -1.42
    orean
    -1.41
     freshman
    -1.40
    ately
    -1.40
    POSITIVE LOGITS
    )[@
    1.64
    [@
    1.63
     \-
    1.62
    STM
    1.41
     [@
    1.41
    ptide
    1.38
    doibase
    1.38
    ...]
    1.38
    uding
    1.34
    zb
    1.34
    Activations Density 3.734%

    No Known Activations