© 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. 24299
    Prev
    Next
    INDEX
    Explanations

    structures and expressions relating to personal experiences and societal observations

    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
    23
    +0.17
    1.0%
    497
    +0.11
    0.6%
    197
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.17
    0.01
    266
    +0.11
    -0.02
    15
    +0.10
    0.09
    Negative Logits
    .";
    -1.60
    arde
    -1.46
     program
    -1.46
    ificant
    -1.43
    igenous
    -1.42
     API
    -1.42
    oku
    -1.41
    SDK
    -1.41
    tech
    -1.40
     programming
    -1.40
    POSITIVE LOGITS
    ĻĤ
    1.97
    ľ
    1.78
    ľĵ
    1.75
    »¿
    1.75
    inea
    1.55
    ¶
    1.51
     Dear
    1.51
    Ļª
    1.50
     noon
    1.50
    £
    1.47
    Activations Density 3.325%

    No Known Activations