© 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. 26580
    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/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
    156
    +0.26
    1.6%
    47
    +0.24
    1.4%
    271
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.26
    0.05
    13
    +0.24
    0.06
    47
    +0.17
    0.10
    Negative Logits
    scribe
    -1.65
    blogger
    -1.63
     behalf
    -1.62
     truth
    -1.50
    ento
    -1.47
     brightest
    -1.46
     bye
    -1.43
     yours
    -1.40
    achus
    -1.39
     hers
    -1.36
    POSITIVE LOGITS
    ģ
    3.27
    ļ
    3.08
    Ģ
    2.97
    ħ
    2.92
    ŀ
    2.88
    ĭ
    2.86
    ľ
    2.84
    ĻĤ
    2.77
    £
    2.77
    µ
    2.75
    Activations Density 1.132%

    No Known Activations