© 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. 26754
    Prev
    Next
    INDEX
    Explanations

    the personal pronoun "you" in the text

    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
    185
    +0.14
    0.8%
    104
    +0.13
    0.7%
    294
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.14
    0.02
    104
    +0.13
    0.02
    462
    +0.12
    0.02
    Negative Logits
    $.[]{
    -1.51
    \!\
    -1.43
    []{
    -1.36
    rap
    -1.36
    $–
    -1.34
    '))
    -1.31
    '));
    -1.30
    existent
    -1.28
    ()));
    -1.28
    tract
    -1.27
    POSITIVE LOGITS
     sense
    1.61
    ius
    1.59
    ness
    1.52
    ovich
    1.52
    dorff
    1.51
    sense
    1.45
     Army
    1.45
    pson
    1.44
     Ont
    1.42
    unov
    1.41
    Activations Density 0.051%

    No Known Activations