© 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. 28634
    Prev
    Next
    INDEX
    Explanations

    references to domestic issues or policies

    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
    246
    +0.14
    0.8%
    148
    +0.13
    0.7%
    377
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.14
    0.02
    222
    +0.13
    0.02
    194
    +0.12
    0.02
    Negative Logits
    up
    -1.36
    vereign
    -1.36
    |{\
    -1.36
    with
    -1.34
    oles
    -1.31
    uro
    -1.30
     Trump
    -1.30
    ÑİÑĤ
    -1.28
     admitting
    -1.28
    ONS
    -1.26
    POSITIVE LOGITS
    ĻĤ
    2.67
    Ł
    2.40
    º
    2.35
    ©
    2.30
    »¿
    2.25
    ²
    2.24
    Īĺ
    2.17
    ¿
    2.15
    ¸
    2.12
    °
    2.12
    Activations Density 0.016%

    No Known Activations