© 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. 23746
    Prev
    Next
    INDEX
    Explanations

    mentions of "study" in various contexts

    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
    98
    +0.12
    0.7%
    422
    +0.12
    0.7%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.12
    0.02
    392
    +0.12
    0.02
    488
    +0.11
    0.02
    Negative Logits
    Ļ
    -2.70
    ķ
    -2.48
    ³
    -2.43
    ¥
    -2.42
    «
    -2.34
    ŀ
    -2.31
    ¬
    -2.25
    ĺ
    -2.23
    Ŀ
    -2.10
    Ĺ
    -2.09
    POSITIVE LOGITS
    "}](#
    1.68
    GAN
    1.57
    verte
    1.56
    gren
    1.48
     Productions
    1.46
    journals
    1.42
    agna
    1.39
    )](
    1.38
    ÃĹ
    1.38
    wordpress
    1.36
    Activations Density 0.072%

    No Known Activations