© 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. 25190
    Prev
    Next
    INDEX
    Explanations

    assertions or strong statements

    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
    342
    +0.16
    0.9%
    237
    +0.14
    0.8%
    163
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.16
    0.00
    344
    +0.14
    0.00
    244
    +0.12
    0.00
    Negative Logits
    dorff
    -1.78
    Ī
    -1.65
    /-/
    -1.62
    ://
    -1.61
     Sentencing
    -1.45
    Īĺ
    -1.44
    asser
    -1.44
    ·¸
    -1.43
    mark
    -1.42
    -[
    -1.41
    POSITIVE LOGITS
    lor
    1.73
    ate
    1.71
    late
    1.65
    pieces
    1.60
    pired
    1.57
    olate
    1.55
     views
    1.44
    idea
    1.44
     mind
    1.43
    arters
    1.42
    Activations Density 0.000%

    No Known Activations