© 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. 24525
    Prev
    Next
    INDEX
    Explanations

    annotations and metadata in code

    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
    181
    +0.13
    0.7%
    156
    +0.12
    0.7%
    338
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.13
    0.02
    275
    +0.12
    0.01
    171
    +0.11
    0.01
    Negative Logits
    >';
    -1.65
     &$
    -1.48
    $’
    -1.40
    '];
    -1.39
     times
    -1.38
    :&
    -1.37
    '=>
    -1.36
    '));
    -1.36
    >$
    -1.36
    '>
    -1.36
    POSITIVE LOGITS
     herself
    1.79
    ment
    1.68
    itz
    1.62
    ĻĤ
    1.61
    ĵ
    1.58
    hower
    1.58
    §
    1.55
    iment
    1.48
    ites
    1.43
    anges
    1.42
    Activations Density 0.108%

    No Known Activations