© 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. 25081
    Prev
    Next
    INDEX
    Explanations

    references to software and licensing terms

    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
    352
    +0.13
    0.7%
    23
    +0.13
    0.7%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.13
    0.01
    237
    +0.13
    0.01
    452
    +0.11
    0.01
    Negative Logits
     PBX
    -1.86
    amente
    -1.66
    ahi
    -1.63
    "));
    -1.59
     WARRANTY
    -1.58
    edly
    -1.57
    enium
    -1.55
    /
    -1.53
     warranty
    -1.45
    arium
    -1.44
    POSITIVE LOGITS
    Ļª
    2.40
    ¿½
    2.27
    ij
    2.23
    ©
    2.22
    Īĺ
    2.21
    ·
    2.16
    IJ
    2.09
    Ĺ
    2.03
    Ń
    2.02
    ĻĤ
    1.98
    Activations Density 0.058%

    No Known Activations