© 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. 30092
    Prev
    Next
    INDEX
    Explanations

    instances of steepness or steep slopes

    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
    111
    +0.15
    0.8%
    317
    +0.13
    0.7%
    295
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    317
    +0.13
    0.01
    80
    +0.13
    0.01
    Negative Logits
    erald
    -1.58
    ost
    -1.45
    ureus
    -1.43
    ras
    -1.36
    uge
    -1.33
    oston
    -1.31
     Wales
    -1.31
    ories
    -1.29
    rely
    -1.28
     vast
    -1.27
    POSITIVE LOGITS
    ¢
    4.08
    Īĺ
    3.88
    ¨
    3.68
    ¸
    3.62
    ł
    3.57
    Ļ
    3.55
    ĸ
    3.53
    ·
    3.46
    ²
    3.44
    ĻĤ
    3.44
    Activations Density 0.015%

    No Known Activations