© 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. 0-MLP-SM
    11. 30172
    Prev
    Next
    INDEX
    Explanations

    references to images and their attributes

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    100
    +0.13
    0.7%
    269
    +0.11
    0.6%
    391
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.13
    0.02
    464
    +0.11
    0.01
    363
    +0.10
    0.01
    Negative Logits
    Īĺ
    -3.44
    Ń
    -3.37
    ľĵ
    -3.07
    Ĥ
    -3.03
    Ĥ¬
    -2.99
    ĨĴ
    -2.98
    ³
    -2.93
    IJ
    -2.92
    ½
    -2.92
    ·¸
    -2.89
    POSITIVE LOGITS
     cavity
    1.73
     arsenal
    1.70
    picture
    1.68
    processor
    1.64
     remains
    1.62
     scene
    1.57
     caption
    1.55
    cdn
    1.55
     tag
    1.52
    wiki
    1.52
    Activations Density 0.025%

    No Known Activations