© 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. 9659
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to healthcare, regulations, and agency operations

    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
    186
    +0.13
    0.8%
    155
    +0.12
    0.7%
    422
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.13
    0.03
    422
    +0.12
    0.06
    256
    +0.12
    0.13
    Negative Logits
    ço
    -1.73
    backs
    -1.60
     lightly
    -1.53
    ires
    -1.51
    ools
    -1.43
     brow
    -1.37
    anges
    -1.37
    sembles
    -1.35
    lessly
    -1.35
     fast
    -1.34
    POSITIVE LOGITS
    *.*
    1.88
    Âł↵
    1.63
    ).](
    1.57
    .^[@
    1.48
    *.,
    1.48
    RON
    1.47
    *.
    1.46
    .](
    1.45
    Âł
    1.45
     Federation
    1.44
    Activations Density 5.661%

    No Known Activations