© 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. 30474
    Prev
    Next
    INDEX
    Explanations

    expressions of strong beliefs or sentiments

    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
    156
    +0.21
    1.2%
    376
    +0.18
    1.1%
    199
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.21
    0.02
    127
    +0.18
    0.02
    255
    +0.14
    0.02
    Negative Logits
    ©
    -3.19
    ´
    -3.08
    ĥ½
    -3.05
    ŀ
    -3.00
    ĸ´
    -2.90
    ·¸
    -2.88
    º
    -2.77
    ¸
    -2.74
    ±
    -2.69
    Ĭ
    -2.64
    POSITIVE LOGITS
     enough
    2.08
     urge
    1.48
    áĢ¬
    1.45
     impulse
    1.43
     discourage
    1.37
    enough
    1.36
    rics
    1.36
     discouraged
    1.31
     suggest
    1.31
     encourage
    1.29
    Activations Density 0.019%

    No Known Activations