© 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. 24982
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics

    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
    216
    +0.12
    0.6%
    317
    +0.12
    0.6%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.12
    0.06
    414
    +0.12
    0.02
    82
    +0.11
    0.03
    Negative Logits
    ¾
    -3.32
    Ľ
    -3.14
    Ħ
    -3.08
    ²
    -3.08
    Ŀ
    -3.08
    Ń
    -3.07
    Ļ
    -3.03
    ±
    -2.97
    Ĥ
    -2.93
    ľ
    -2.89
    POSITIVE LOGITS
    CDATA
    1.54
    ahoma
    1.49
    mozilla
    1.49
     Mortgage
    1.47
    REE
    1.47
    anian
    1.43
    ERK
    1.43
     Financial
    1.41
    cdn
    1.41
    ournal
    1.40
    Activations Density 0.577%

    No Known Activations