© 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. 26606
    Prev
    Next
    INDEX
    Explanations

    terms related to medical injections

    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
    +0.20
    1.1%
    344
    +0.13
    0.8%
    42
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.20
    0.02
    177
    +0.13
    0.01
    148
    +0.11
    0.00
    Negative Logits
     geneal
    -1.56
     MERCHANTABILITY
    -1.56
    fully
    -1.55
    ãĤĥ
    -1.46
     medieval
    -1.46
     inheritance
    -1.45
     nesting
    -1.45
     pirates
    -1.44
    izen
    -1.43
    ighb
    -1.42
    POSITIVE LOGITS
     injection
    1.61
    inator
    1.57
    ulsion
    1.56
     needle
    1.56
    raph
    1.54
    rate
    1.52
     timed
    1.50
    inated
    1.50
    gun
    1.49
    injection
    1.49
    Activations Density 0.110%

    No Known Activations