© 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. 26728
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "interferon."

    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
    111
    +0.13
    0.7%
    93
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.01
    71
    +0.12
    0.01
    344
    +0.12
    0.01
    Negative Logits
    Ĥ¬
    -2.61
    ĥ½
    -2.57
    ĥ
    -2.54
    ĺ
    -2.48
    ľĵ
    -2.37
    ĸ´
    -2.34
    Ļ
    -2.28
    ¿½
    -2.25
    ·
    -2.21
    Ĭ
    -2.17
    POSITIVE LOGITS
    nikov
    1.67
     panel
    1.67
     gaug
    1.59
     panels
    1.54
     tracker
    1.51
     chamber
    1.40
     compartment
    1.38
    hardt
    1.35
     gamma
    1.34
     system
    1.33
    Activations Density 0.007%

    No Known Activations