© 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. 23071
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal data and privacy matters

    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
    21
    +0.13
    0.7%
    307
    +0.13
    0.7%
    5
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.08
    5
    +0.13
    0.06
    78
    +0.12
    0.05
    Negative Logits
    caster
    -1.54
    lez
    -1.52
    ching
    -1.52
    road
    -1.40
    .[
    -1.38
    orb
    -1.38
    voir
    -1.37
    kit
    -1.35
    aster
    -1.32
    tip
    -1.32
    POSITIVE LOGITS
    Ī
    4.39
    °
    4.23
    Į
    4.11
    Īĺ
    4.02
    ĺ
    3.91
    Ł
    3.91
    ĥ½
    3.90
    ŀ
    3.88
    İ
    3.87
    ¿
    3.83
    Activations Density 1.585%

    No Known Activations