© 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. 2-MLP-SM
    11. 23992
    Prev
    Next
    INDEX
    Explanations

    references to indigenous peoples and their territories

    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/2-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.2.hook_mlp_out
    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
    324
    +0.12
    0.7%
    290
    +0.11
    0.6%
    274
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.10
    239
    +0.11
    0.12
    409
    +0.10
    0.11
    Negative Logits
    ·¸
    -2.04
    ¿½
    -2.00
    ©
    -2.00
    ¿
    -1.92
    Ł
    -1.92
    ¦
    -1.89
    ł
    -1.82
    ²
    -1.80
    ĻĤ
    -1.79
    ®
    -1.77
    POSITIVE LOGITS
    idd
    1.62
    ags
    1.54
    udad
    1.50
    ellee
    1.50
    ipore
    1.44
    okrat
    1.42
    ulsion
    1.42
     Municip
    1.41
    uru
    1.40
    lite
    1.39
    Activations Density 3.318%

    No Known Activations