© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-MLP-SM
    11. 27044
    Prev
    Next
    INDEX
    Explanations

    references to dates

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    47
    +0.15
    0.9%
    267
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.15
    0.03
    485
    +0.14
    0.02
    66
    +0.13
    0.02
    Negative Logits
    ĻĤ
    -2.03
    esso
    -1.79
    iary
    -1.74
     sexually
    -1.63
    Ľ
    -1.63
    edly
    -1.60
    enium
    -1.56
     filing
    -1.54
    jor
    -1.54
     filed
    -1.53
    POSITIVE LOGITS
     behold
    1.63
     [-
    1.60
     dB
    1.56
     opponents
    1.52
     Reaction
    1.48
     rivals
    1.44
     impulse
    1.42
     rival
    1.40
     regenerative
    1.40
     momentum
    1.37
    Activations Density 0.052%

    No Known Activations