© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    terms related to medical implants and their associated issues

    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
    136
    +0.15
    0.9%
    505
    +0.12
    0.7%
    167
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.15
    0.01
    167
    +0.12
    0.03
    185
    +0.11
    0.02
    Negative Logits
    het
    -1.47
    .’
    -1.46
    .’”
    -1.45
     respectively
    -1.33
    ...](
    -1.32
    []{
    -1.29
     statewide
    -1.28
    hift
    -1.25
     working
    -1.25
     arms
    -1.25
    POSITIVE LOGITS
    ¾
    2.78
    ĥ½
    2.77
    Ĵ
    2.75
    Ĥ¬
    2.70
    ĺ
    2.69
    ´
    2.59
    Ł
    2.58
    ¤
    2.55
    §
    2.53
    ł
    2.52
    Activations Density 0.121%

    No Known Activations