© 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. 29865
    Prev
    Next
    INDEX
    Explanations

    instances of the word "broken"

    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
    376
    +0.17
    1.0%
    276
    +0.15
    0.8%
    256
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.17
    0.02
    313
    +0.15
    0.01
    423
    +0.12
    0.01
    Negative Logits
    anner
    -1.60
    ORT
    -1.40
    Ĥ
    -1.38
    Cle
    -1.37
    ONS
    -1.36
     Clear
    -1.33
    AMS
    -1.25
     lighter
    -1.24
    acement
    -1.24
     flushed
    -1.23
    POSITIVE LOGITS
    hearted
    2.10
    gart
    1.84
    oku
    1.75
    heim
    1.72
    ji
    1.69
    ÅĦ
    1.67
    etics
    1.64
    hov
    1.63
    ball
    1.59
    heimer
    1.59
    Activations Density 0.028%

    No Known Activations