© 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. 28178
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or emphasis on specific elements in the text

    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
    112
    +0.14
    0.7%
    497
    +0.13
    0.7%
    257
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.15
    26
    +0.13
    0.14
    199
    +0.11
    0.14
    Negative Logits
    »
    -3.79
    Ĥ¬
    -3.60
    ĥ½
    -3.37
    ĸ´
    -3.27
    ļ
    -3.15
    Īĺ
    -3.11
    ħ
    -3.02
    ĥ
    -2.97
    Ľ
    -2.97
    ¡
    -2.94
    POSITIVE LOGITS
    actic
    1.48
    etic
    1.45
    icion
    1.44
    sk
    1.41
    choline
    1.40
     correspond
    1.39
    new
    1.36
    tech
    1.32
    sov
    1.30
     van
    1.29
    Activations Density 0.274%

    No Known Activations