© 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. 30108
    Prev
    Next
    INDEX
    Explanations

    references to the Federal Reserve

    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
    +0.17
    0.9%
    412
    +0.13
    0.7%
    444
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.17
    0.01
    403
    +0.13
    0.01
    412
    +0.11
    0.01
    Negative Logits
    upon
    -1.87
     miscar
    -1.62
    ---|---
    -1.45
    soever
    -1.44
     disbelief
    -1.40
     False
    -1.40
    ockey
    -1.40
    thood
    -1.37
     definite
    -1.37
    abouts
    -1.37
    POSITIVE LOGITS
    ĻĤ
    2.71
    »¿
    2.52
    Į
    2.49
    Ĩ
    2.43
    Īĺ
    2.29
    ®
    2.23
    ½
    2.22
    ¡
    2.21
    °
    2.19
    ĺ
    2.19
    Activations Density 0.011%

    No Known Activations