© 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. 10696
    Prev
    Next
    INDEX
    Explanations

    terms associated with medical conditions and their related factors

    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
    231
    +0.16
    0.9%
    226
    +0.12
    0.7%
    11
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.16
    0.06
    162
    +0.12
    0.06
    29
    +0.12
    0.03
    Negative Logits
    ect
    -1.40
    gem
    -1.40
     lt
    -1.37
     FROM
    -1.36
     habit
    -1.35
    ativ
    -1.24
    kan
    -1.23
    atement
    -1.23
    sizeof
    -1.23
     commanded
    -1.22
    POSITIVE LOGITS
    Ļ
    2.71
    Ł
    2.30
    ³
    2.25
    ľ
    2.24
    ¾
    2.19
    ł
    2.13
    ¨
    2.12
    ¹
    2.09
    »¿
    2.06
    Ķ
    1.98
    Activations Density 0.305%

    No Known Activations