© 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. 26336
    Prev
    Next
    INDEX
    Explanations

    references to monkeys and other primates

    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
    156
    +0.14
    0.8%
    466
    +0.12
    0.7%
    14
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.14
    0.03
    156
    +0.12
    0.03
    264
    +0.12
    0.03
    Negative Logits
    ĺ
    -4.41
    ¶
    -4.38
    ī
    -4.36
    IJ
    -4.27
    ©
    -4.23
    Ĺ
    -4.21
    Ħ
    -4.18
    º
    -4.15
    Ķ
    -4.12
    µ
    -4.09
    POSITIVE LOGITS
    fish
    1.77
    izumab
    1.75
    onomy
    1.55
    raz
    1.53
    ards
    1.51
    ishly
    1.47
    like
    1.46
    phrine
    1.44
    deen
    1.41
    ifically
    1.37
    Activations Density 0.078%

    No Known Activations