© 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. 29446
    Prev
    Next
    INDEX
    Explanations

    references to a specific law firm

    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
    369
    +0.17
    1.0%
    111
    +0.16
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.01
    338
    +0.16
    0.01
    369
    +0.13
    0.01
    Negative Logits
     certain
    -1.65
     particular
    -1.53
    ffect
    -1.51
    ircraft
    -1.46
    ories
    -1.46
     pirate
    -1.42
     comb
    -1.35
     Westminster
    -1.34
    illance
    -1.34
    ly
    -1.32
    POSITIVE LOGITS
    etz
    1.91
    ilee
    1.86
    (%
    1.74
    dimen
    1.69
    sizeof
    1.58
    fors
    1.51
    eful
    1.49
    ved
    1.49
    ungen
    1.45
    inger
    1.45
    Activations Density 0.014%

    No Known Activations