© 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. 25647
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the term "client"

    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
    1.3%
    376
    +0.13
    0.8%
    73
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.22
    0.03
    347
    +0.13
    0.02
    343
    +0.12
    0.02
    Negative Logits
    woke
    -2.07
     Columbia
    -1.58
    ><
    -1.57
     authors
    -1.42
     transgender
    -1.42
    ÑĤÑĮ
    -1.40
     longer
    -1.39
    utz
    -1.38
    aintiff
    -1.38
    >$
    -1.36
    POSITIVE LOGITS
    het
    2.37
    ele
    2.11
    iles
    1.92
    ily
    1.91
    ile
    1.69
    ielle
    1.65
    pieces
    1.61
    dom
    1.56
    etable
    1.52
    ell
    1.51
    Activations Density 0.442%

    No Known Activations