© 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. 29877
    Prev
    Next
    INDEX
    Explanations

    references to Russia and its associated 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
    227
    +0.13
    0.7%
    105
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.03
    227
    +0.12
    0.03
    180
    +0.12
    0.02
    Negative Logits
    usterity
    -1.69
     colorectal
    -1.62
    assing
    -1.61
    zing
    -1.60
    aging
    -1.48
     ich
    -1.47
    atinib
    -1.47
    '))
    -1.39
     gastrointestinal
    -1.37
    lando
    -1.36
    POSITIVE LOGITS
    craft
    1.84
    borg
    1.76
    lei
    1.74
    ians
    1.73
    finder
    1.66
     herself
    1.62
    heet
    1.58
    FW
    1.58
     ÂĹ
    1.55
    fors
    1.54
    Activations Density 0.030%

    No Known Activations