© 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. 2-RES-SM
    11. 10463
    Prev
    Next
    INDEX
    Explanations

    terms related to phosphorous and its compounds

    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
    148
    +0.12
    0.7%
    111
    +0.12
    0.7%
    354
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.01
    148
    +0.12
    0.01
    48
    +0.11
    0.01
    Negative Logits
    ward
    -1.88
     hesitation
    -1.75
    wards
    -1.75
    ALLY
    -1.59
     alia
    -1.58
     miscar
    -1.55
    pired
    -1.54
     prospective
    -1.53
    uvant
    -1.51
     unsuccessful
    -1.47
    POSITIVE LOGITS
    orescent
    1.83
    orous
    1.70
    uric
    1.57
    uble
    1.56
    ethanol
    1.55
    electric
    1.51
    aces
    1.50
    ensing
    1.48
    aced
    1.48
    glycer
    1.47
    Activations Density 0.059%

    No Known Activations