© 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. 2-MLP-SM
    11. 25108
    Prev
    Next
    INDEX
    Explanations

    references to wars and significant historical events, particularly World War contexts

    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
    66
    +0.15
    0.8%
    462
    +0.14
    0.8%
    355
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.15
    0.09
    364
    +0.14
    0.07
    462
    +0.12
    0.03
    Negative Logits
    itting
    -1.66
    abbing
    -1.66
    ipl
    -1.63
    ashing
    -1.53
    ipple
    -1.53
     digging
    -1.53
    alling
    -1.45
    printf
    -1.42
     fighting
    -1.41
    ash
    -1.41
    POSITIVE LOGITS
     agent
    1.71
    owski
    1.57
     [(\[
    1.54
    "}](#
    1.48
     cerevisiae
    1.48
     agents
    1.48
     outwe
    1.48
     VIII
    1.47
    .]{}
    1.47
    uate
    1.47
    Activations Density 1.368%

    No Known Activations