© 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. 24699
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in text

    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
    482
    +0.15
    0.8%
    212
    +0.13
    0.7%
    220
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.15
    0.10
    212
    +0.13
    0.09
    220
    +0.12
    0.09
    Negative Logits
    °
    -2.19
    ½
    -2.17
    µ
    -2.13
    ·
    -2.09
    IJ
    -2.09
    ı
    -2.08
    ĨĴ
    -2.06
    ª
    -2.05
    ¡
    -1.99
    ĥ½
    -1.97
    POSITIVE LOGITS
    wg
    1.56
    zig
    1.51
     altogether
    1.51
    FG
    1.45
    cribing
    1.42
    fire
    1.36
    glass
    1.35
    hops
    1.29
    hop
    1.29
    limiting
    1.28
    Activations Density 2.047%

    No Known Activations