© 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. 24233
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables in equations

    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
    23
    +0.13
    0.7%
    271
    +0.12
    0.7%
    381
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.02
    82
    +0.12
    0.01
    235
    +0.12
    0.03
    Negative Logits
    hoe
    -1.63
     Chern
    -1.61
    dor
    -1.60
    iewicz
    -1.57
    lei
    -1.51
    vier
    -1.48
    iscus
    -1.48
    ille
    -1.47
    ?**
    -1.47
    googleapis
    -1.46
    POSITIVE LOGITS
    ĻĤ
    2.48
    Ĩ
    2.38
    ³
    2.24
    °
    2.21
    ·
    2.19
    µ
    2.11
    ĥ
    2.10
    Ĥ¬
    2.04
    ĥ½
    2.03
    ¯
    1.99
    Activations Density 0.362%

    No Known Activations