© 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. 30032
    Prev
    Next
    INDEX
    Explanations

    numerical values and counts

    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
    354
    +0.13
    0.8%
    350
    +0.12
    0.7%
    392
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.06
    56
    +0.12
    0.01
    23
    +0.11
    0.05
    Negative Logits
     integrity
    -1.49
     same
    -1.48
     visitor
    -1.47
     thee
    -1.44
     abruptly
    -1.42
     Reverend
    -1.40
    tait
    -1.40
     like
    -1.38
    matically
    -1.38
     #{
    -1.38
    POSITIVE LOGITS
    etable
    2.55
    eric
    2.24
    etica
    1.92
    stro
    1.88
    ero
    1.87
    cule
    1.87
    ematic
    1.86
    esis
    1.85
    elli
    1.85
    etto
    1.82
    Activations Density 6.546%

    No Known Activations