© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and 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
    +0.22
    1.3%
    246
    +0.15
    0.9%
    119
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.22
    0.01
    218
    +0.15
    0.02
    443
    +0.11
    0.02
    Negative Logits
    mith
    -1.97
    antly
    -1.88
    mons
    -1.87
    back
    -1.79
    ban
    -1.66
    itarian
    -1.63
    izations
    -1.63
     myself
    -1.62
    imum
    -1.62
    backs
    -1.59
    POSITIVE LOGITS
    rocyte
    2.09
    roid
    1.96
    ĥ
    1.90
    ĻĤ
    1.84
    ı
    1.76
    romycin
    1.70
    ECT
    1.70
    rosine
    1.60
    resses
    1.60
    radiol
    1.59
    Activations Density 0.126%

    No Known Activations