© 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. MLP Post
    9. 0-MLP-SM
    11. 26236
    Prev
    Next
    INDEX
    Explanations

    locations or abbreviations related to Texas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    369
    +0.20
    1.1%
    376
    +0.11
    0.6%
    18
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.20
    0.01
    320
    +0.11
    0.01
    213
    +0.11
    0.01
    Negative Logits
    iginally
    -1.82
     yours
    -1.82
    cluding
    -1.80
     else
    -1.78
     Parenthood
    -1.63
    ĥ½
    -1.55
    oxacin
    -1.53
    actic
    -1.53
    apolis
    -1.51
    ĩ
    -1.45
    POSITIVE LOGITS
    emaker
    1.78
    ÃŃo
    1.65
    enos
    1.65
    ourier
    1.61
    ena
    1.61
    ilt
    1.60
    igt
    1.60
    iens
    1.58
    edo
    1.58
    illac
    1.56
    Activations Density 0.010%

    No Known Activations