© 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. 0-MLP-SM
    11. 26723
    Prev
    Next
    INDEX
    Explanations

    the word "also" used repeatedly to emphasize additional information or points

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    130
    +0.16
    0.9%
    250
    +0.12
    0.7%
    392
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.16
    0.03
    250
    +0.12
    0.02
    392
    +0.12
    0.02
    Negative Logits
    ģ
    -2.47
    Ģ
    -2.43
    ħ
    -2.36
    ĥ½
    -2.30
    º
    -2.20
    ij
    -2.06
    ĩ
    -2.06
    iously
    -1.88
    ĭ
    -1.88
    antly
    -1.87
    POSITIVE LOGITS
    acute
    1.44
    Court
    1.36
     None
    1.33
    ÅĦ
    1.33
    mus
    1.32
    remia
    1.31
    None
    1.30
    ···
    1.29
    birth
    1.28
     Publication
    1.28
    Activations Density 0.156%

    No Known Activations