© 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. 25619
    Prev
    Next
    INDEX
    Explanations

    references to jury and verdict-related terms in legal contexts

    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
    72
    +0.12
    0.7%
    42
    +0.11
    0.7%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.12
    0.03
    349
    +0.11
    0.03
    72
    +0.11
    0.03
    Negative Logits
    Č
    -1.96
     monoton
    -1.60
    Drosophila
    -1.38
    \>
    -1.36
    ```
    -1.35
     faint
    -1.35
    ATES
    -1.34
    enberg
    -1.32
    ^*
    -1.31
     contrary
    -1.31
    POSITIVE LOGITS
    craft
    1.72
    pieces
    1.70
    fare
    1.64
    fix
    1.60
    ceedings
    1.56
    ive
    1.55
    blems
    1.52
    rectomy
    1.51
    ivals
    1.50
    esy
    1.50
    Activations Density 0.056%

    No Known Activations