© 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. 23752
    Prev
    Next
    INDEX
    Explanations

    references to digital media and technology usage

    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
    291
    +0.12
    0.7%
    214
    +0.12
    0.6%
    446
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.02
    164
    +0.12
    0.02
    291
    +0.11
    0.01
    Negative Logits
     BA
    -1.50
    ocyte
    -1.49
    ichi
    -1.47
    ://
    -1.44
     touchdowns
    -1.41
    Sat
    -1.39
     readers
    -1.36
    åĬ¡
    -1.36
    zeit
    -1.34
    ynaptic
    -1.33
    POSITIVE LOGITS
    ¯
    2.57
    Ł
    2.56
    ĩ
    2.32
    ĺ
    2.32
    °
    2.29
    ł
    2.25
    ·
    2.25
    ¾
    2.23
    ¡
    2.18
    Ŀ
    2.16
    Activations Density 0.202%

    No Known Activations