© 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. 29576
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values and references to numbers

    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
    156
    +0.22
    1.2%
    224
    +0.12
    0.7%
    249
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.22
    0.01
    262
    +0.12
    0.01
    287
    +0.11
    0.01
    Negative Logits
     me
    -1.84
    /-
    -1.58
    iving
    -1.43
    opes
    -1.43
    ived
    -1.42
    ÑĤÑĮ
    -1.42
    rying
    -1.41
    ĥ½
    -1.37
    iginal
    -1.36
    ères
    -1.36
    POSITIVE LOGITS
     elsewhere
    1.71
    enza
    1.70
    etti
    1.68
    quel
    1.66
    entes
    1.54
    itone
    1.52
    ubuntu
    1.51
    istar
    1.45
    enti
    1.44
    ulator
    1.42
    Activations Density 0.022%

    No Known Activations