© 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. 23241
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal processes and procedures

    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
    1
    +0.13
    0.7%
    29
    +0.11
    0.6%
    84
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.13
    0.02
    67
    +0.11
    0.02
    421
    +0.10
    0.02
    Negative Logits
    ĥ½
    -2.33
    ij
    -2.27
    Ĺ
    -2.25
    ĺ
    -2.23
    ŀ
    -2.12
    ·
    -2.09
    ĥ
    -2.08
    »
    -2.01
    Ī
    -2.01
    µ
    -1.99
    POSITIVE LOGITS
    buntu
    1.70
    ULAR
    1.70
    pora
    1.60
    strap
    1.60
    OPLE
    1.59
    ncia
    1.52
    itrile
    1.50
    ARS
    1.50
    ambda
    1.49
    dL
    1.49
    Activations Density 0.064%

    No Known Activations