© 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. 2-MLP-SM
    11. 22875
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "em" 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.19
    1.1%
    27
    +0.13
    0.7%
    4
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.19
    0.01
    18
    +0.13
    0.01
    40
    +0.12
    0.01
    Negative Logits
    Ľ
    -2.79
    ¿
    -2.39
    ĥ½
    -2.37
    Ĥ
    -2.30
    į
    -2.28
    Ī
    -2.27
    £
    -2.26
    ¼
    -2.21
    §
    -2.20
    ĨĴ
    -2.18
    POSITIVE LOGITS
    itus
    1.55
    ricanes
    1.47
    apa
    1.45
     bus
    1.42
    olson
    1.35
    iels
    1.35
    rg
    1.34
    ray
    1.32
    itting
    1.32
    ilo
    1.29
    Activations Density 0.240%

    No Known Activations