© 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. 26114
    Prev
    Next
    INDEX
    Explanations

    strong affirmations or emphatic 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/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
    +0.22
    1.3%
    376
    +0.21
    1.2%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.22
    0.02
    40
    +0.21
    0.02
    432
    +0.13
    0.02
    Negative Logits
    Ľ
    -1.73
    ĥ½
    -1.68
    ĭ
    -1.65
    ureus
    -1.61
    ĨĴ
    -1.54
    ele
    -1.53
    bie
    -1.52
    rock
    -1.52
    ymphony
    -1.51
    glich
    -1.51
    POSITIVE LOGITS
    deal
    1.65
     movements
    1.53
     clashes
    1.48
     encounter
    1.47
     attacks
    1.44
     hurt
    1.41
     exist
    1.38
     DAMAGE
    1.35
    acted
    1.35
    quit
    1.34
    Activations Density 0.465%

    No Known Activations