© 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. 4-RES-SM
    11. 11308
    Prev
    Next
    INDEX
    Explanations

    words related to anti-thrombosis or anticoagulant treatments

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.15
    0.9%
    501
    +0.11
    0.6%
    203
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.15
    0.01
    187
    +0.11
    0.01
    218
    +0.10
    0.01
    Negative Logits
    blogger
    -1.85
    king
    -1.76
    roup
    -1.44
    cence
    -1.43
    quilibrium
    -1.43
    ancy
    -1.42
    back
    -1.41
    ker
    -1.38
     mean
    -1.37
    quez
    -1.36
    POSITIVE LOGITS
    Ī
    3.28
    ¶
    3.23
    Į
    3.21
    ¤
    3.16
    IJ
    3.12
    ĥ
    3.07
    ¯
    3.05
    3.00
    3.00
    3.00
    Activations Density 0.067%

    No Known Activations