© 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. 23649
    Prev
    Next
    INDEX
    Explanations

    refers to an item or element within a list or collection

    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
    107
    +0.12
    0.7%
    455
    +0.12
    0.7%
    495
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.12
    0.03
    23
    +0.12
    0.01
    120
    +0.12
    0.03
    Negative Logits
     inches
    -1.60
     kilometers
    -1.56
    bearing
    -1.56
     miles
    -1.55
    )?
    -1.51
     kilometres
    -1.49
     meters
    -1.48
    km
    -1.46
    lines
    -1.46
    lined
    -1.46
    POSITIVE LOGITS
     import
    1.58
     contradiction
    1.54
    jor
    1.45
     result
    1.41
    öm
    1.38
    ases
    1.36
     question
    1.34
     dissent
    1.32
    ano
    1.31
     dissociation
    1.30
    Activations Density 0.197%

    No Known Activations