© 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. 26007
    Prev
    Next
    INDEX
    Explanations

    the word "el" in various contexts

    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
    369
    +0.13
    0.7%
    222
    +0.12
    0.6%
    175
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.13
    0.02
    175
    +0.12
    0.01
    137
    +0.10
    0.01
    Negative Logits
    "))
    -1.71
    ")]
    -1.57
    )\|_{
    -1.57
     separate
    -1.51
    .")
    -1.48
    ").
    -1.48
    stitution
    -1.45
    "));
    -1.42
    "].
    -1.40
    '));
    -1.39
    POSITIVE LOGITS
    ĻĤ
    2.74
    ©
    2.56
    ¸
    2.55
    ĨĴ
    2.48
    Ľ
    2.38
    ·
    2.30
    ¯
    2.30
    º
    2.21
    §
    2.21
    ĸ´
    2.21
    Activations Density 0.064%

    No Known Activations