© 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. 1-RES-SM
    11. 24777
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and anatomical references, particularly focusing on back pain and related injuries

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    190
    +0.13
    0.8%
    0
    +0.13
    0.7%
    272
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.13
    0.04
    501
    +0.13
    0.03
    186
    +0.11
    -0.00
    Negative Logits
    ¬
    -2.20
    ĨĴ
    -2.18
    ¿½
    -2.11
    ¯
    -2.06
    ·
    -1.91
    ¶
    -1.91
    ©
    -1.81
    Īĺ
    -1.79
    ¢
    -1.79
    ¦
    -1.76
    POSITIVE LOGITS
    ingu
    1.78
    umab
    1.71
    Åij
    1.70
    ÅĽci
    1.64
    imester
    1.63
    holder
    1.62
    ferent
    1.61
    edia
    1.60
    izumab
    1.58
    views
    1.58
    Activations Density 0.800%

    No Known Activations