© 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. 29027
    Prev
    Next
    INDEX
    Explanations

    instances of communication-related terms

    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
    0.9%
    111
    +0.12
    0.7%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    510
    +0.12
    0.01
    84
    +0.12
    0.01
    Negative Logits
    wards
    -1.84
    ĨĴ
    -1.70
    ward
    -1.56
    Ļª
    -1.43
    vere
    -1.42
    ellow
    -1.38
    ®
    -1.36
    >();
    -1.35
     dire
    -1.31
    TO
    -1.30
    POSITIVE LOGITS
    ariate
    1.71
    ibus
    1.62
     factor
    1.52
     mmol
    1.51
    acle
    1.43
    acles
    1.43
    imals
    1.41
     Stats
    1.40
     ANOVA
    1.40
    anium
    1.37
    Activations Density 0.297%

    No Known Activations