© 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. 26741
    Prev
    Next
    INDEX
    Explanations

    references to a specific legal entity or court structure

    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%
    251
    +0.10
    0.6%
    362
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.12
    0.01
    370
    +0.10
    0.01
    44
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.92
    ĨĴ
    -2.16
    Ģ
    -2.14
    Į
    -2.12
    ĥ
    -1.88
    Ħ
    -1.88
    ²
    -1.87
    Ī
    -1.84
    ħ
    -1.82
    Ļª
    -1.82
    POSITIVE LOGITS
    films
    1.67
    plates
    1.66
    ÃŃf
    1.63
    hips
    1.60
    film
    1.59
    plant
    1.55
     Award
    1.53
    ised
    1.50
     feat
    1.50
    wiki
    1.48
    Activations Density 0.011%

    No Known Activations