© 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. 0-MLP-SM
    11. 26534
    Prev
    Next
    INDEX
    Explanations

    references to the word "ren" in various 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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    108
    +0.12
    0.7%
    330
    +0.12
    0.7%
    232
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.12
    0.03
    232
    +0.12
    0.02
    140
    +0.12
    0.02
    Negative Logits
    ?'
    -1.81
    ?).
    -1.78
    '?"
    -1.67
    LLOW
    -1.61
    '))
    -1.59
    '));
    -1.59
     ?"
    -1.58
    upon
    -1.54
     brightest
    -1.53
    ?"
    -1.47
    POSITIVE LOGITS
    ergy
    1.87
    derer
    1.78
    bies
    1.68
     shots
    1.68
    imir
    1.65
    naissance
    1.49
    unci
    1.49
    castle
    1.49
     composer
    1.45
    unciation
    1.45
    Activations Density 1.623%

    No Known Activations