© 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 EvalsExportsAPI 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. 28894
    Prev
    Next
    INDEX
    Explanations

    the word "confirmed."

    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
    +0.25
    1.5%
    148
    +0.18
    1.0%
    443
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.25
    0.03
    248
    +0.18
    0.02
    339
    +0.17
    0.02
    Negative Logits
    omorphism
    -1.66
    ĨĴ
    -1.55
    ainen
    -1.53
    ustr
    -1.45
     argued
    -1.45
    lli
    -1.44
    enue
    -1.44
    ributed
    -1.43
    »¿
    -1.43
    ille
    -1.42
    POSITIVE LOGITS
    tons
    1.48
     sending
    1.40
     shots
    1.36
    ités
    1.35
     rumors
    1.33
     who
    1.32
    mortem
    1.31
     ending
    1.31
    Pros
    1.30
    —"
    1.28
    Activations Density 0.013%

    No Known Activations