© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    engineering and technical specifications related to computer hardware

    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
    156
    +0.20
    1.1%
    123
    +0.15
    0.9%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.20
    0.05
    329
    +0.15
    0.04
    332
    +0.14
    0.06
    Negative Logits
     CIRCUIT
    -1.58
    amycin
    -1.57
     ?>
    -1.47
    ureus
    -1.47
    ük
    -1.44
    ème
    -1.37
    "}](#
    -1.37
    ün
    -1.36
    NdEx
    -1.35
    ?>
    -1.34
    POSITIVE LOGITS
    ļ
    1.99
    ®
    1.95
    º
    1.79
    Ĺ
    1.72
    ĥ
    1.68
    ¶
    1.66
    psy
    1.63
    Ļª
    1.62
    Ĩ
    1.53
    IJ
    1.52
    Activations Density 0.522%

    No Known Activations