© 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 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. 10443
    Prev
    Next
    INDEX
    Explanations

    references to nature and environmental elements

    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
    234
    +0.13
    0.7%
    407
    +0.12
    0.7%
    12
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.13
    0.14
    130
    +0.12
    0.16
    407
    +0.11
    0.11
    Negative Logits
    watson
    -2.04
     —
    -1.92
     ÂĹ
    -1.63
     Harbor
    -1.62
     Milwaukee
    -1.56
     Midwest
    -1.55
     Wisconsin
    -1.53
    ÂĹ
    -1.53
     postseason
    -1.52
     offseason
    -1.49
    POSITIVE LOGITS
    ”.
    2.34
     whilst
    2.15
    ’.
    2.09
    '.
    2.08
     etc
    2.04
     till
    2.03
    respectively
    2.02
    ”,
    1.99
    ".
    1.95
     Secondly
    1.94
    Activations Density 4.428%

    No Known Activations