© 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. 30484
    Prev
    Next
    INDEX
    Explanations

    statements asserting or emphasizing a fact

    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
    +0.15
    0.8%
    404
    +0.14
    0.8%
    44
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.04
    44
    +0.14
    0.04
    405
    +0.13
    0.04
    Negative Logits
    enium
    -2.01
     respectively
    -1.43
     yourselves
    -1.42
    .]
    -1.42
    ĨĴ
    -1.40
    InstanceState
    -1.38
     finest
    -1.35
     statistic
    -1.31
    :]
    -1.28
     practice
    -1.27
    POSITIVE LOGITS
    bread
    1.79
    finder
    1.69
    finding
    1.56
    IMO
    1.55
    lessness
    1.50
    iera
    1.47
    uten
    1.45
    itat
    1.44
    ories
    1.43
    oque
    1.36
    Activations Density 0.246%

    No Known Activations