© 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 EvalsExportsAPI 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. 24955
    Prev
    Next
    INDEX
    Explanations

    the concept of an idea or suggestion presented 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
    330
    +0.12
    0.7%
    249
    +0.12
    0.7%
    320
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.12
    0.04
    120
    +0.12
    0.04
    46
    +0.12
    0.03
    Negative Logits
    ĨĴ
    -2.18
    Ļª
    -2.12
    Ľ
    -1.83
    Ģ
    -1.82
    ķ
    -1.76
    )."
    -1.75
    IJ
    -1.68
    ĻĤ
    -1.68
    ľĵ
    -1.66
    Ĺ
    -1.64
    POSITIVE LOGITS
    dere
    1.53
    ably
    1.49
    ely
    1.48
    abol
    1.46
    ken
    1.42
    ke
    1.36
    dern
    1.35
    ord
    1.34
     congrat
    1.30
    legend
    1.29
    Activations Density 0.232%

    No Known Activations