© 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. 13993
    Prev
    Next
    INDEX
    Explanations

    terms associated with spinal and disc health

    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
    +0.21
    1.2%
    71
    +0.13
    0.8%
    343
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.21
    0.01
    18
    +0.13
    0.01
    453
    +0.12
    0.01
    Negative Logits
     precious
    -1.65
     generous
    -1.61
     luck
    -1.60
     forthcoming
    -1.59
     realize
    -1.58
     day
    -1.57
     fierce
    -1.52
     competing
    -1.49
     polite
    -1.44
     gracious
    -1.44
    POSITIVE LOGITS
    ¢
    2.30
    ³
    2.21
    ¬
    2.20
    ·
    2.07
    ĸ
    2.04
    »¿
    2.02
    ŀ
    1.98
    £
    1.97
    ij
    1.93
    Ĥ
    1.92
    Activations Density 0.044%

    No Known Activations