© 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. 2-MLP-SM
    11. 23404
    Prev
    Next
    INDEX
    Explanations

    instances of belonging indicated by the word "to"

    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
    54
    +0.14
    0.7%
    439
    +0.13
    0.7%
    137
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.14
    0.07
    466
    +0.13
    0.07
    160
    +0.11
    0.08
    Negative Logits
    etheless
    -1.63
     ?"
    -1.51
     moment
    -1.50
    terday
    -1.49
    iginally
    -1.44
    unnumbered
    -1.44
    ?",
    -1.41
     opponents
    -1.35
     Methods
    -1.34
     observers
    -1.31
    POSITIVE LOGITS
    Ĵ
    1.56
    orbent
    1.51
    wash
    1.50
     marketed
    1.48
    mmc
    1.47
    ĸ
    1.45
    fill
    1.45
     won
    1.45
    ¤
    1.44
    gets
    1.44
    Activations Density 0.846%

    No Known Activations