© 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. 26246
    Prev
    Next
    INDEX
    Explanations

    references to legal codes or statutes

    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
    97
    +0.16
    1.0%
    184
    +0.13
    0.8%
    123
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.16
    0.01
    184
    +0.13
    0.01
    123
    +0.12
    0.01
    Negative Logits
    '>
    -1.69
    ]>
    -1.68
    -1.63
     ){
    -1.59
    -1.55
    čč
    -1.52
     whole
    -1.51
     ordinary
    -1.50
     answer
    -1.44
     suppose
    -1.43
    POSITIVE LOGITS
    ariate
    1.90
    bian
    1.87
    zilla
    1.83
    enstein
    1.81
    ista
    1.78
    cule
    1.76
    ific
    1.69
    nement
    1.67
    stro
    1.66
    iston
    1.66
    Activations Density 0.027%

    No Known Activations