© 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. 22907
    Prev
    Next
    INDEX
    Explanations

    references to specific judicial districts and courts

    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
    327
    +0.13
    0.7%
    247
    +0.13
    0.7%
    194
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.13
    0.02
    363
    +0.13
    0.01
    8
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.23
     arts
    -1.90
     weddings
    -1.82
    imab
    -1.73
     appeals
    -1.71
     studios
    -1.70
    ¿
    -1.67
     paintings
    -1.63
     appointments
    -1.63
    Īĺ
    -1.62
    POSITIVE LOGITS
    between
    1.80
    ``
    1.80
    observed
    1.76
     ]{}
    1.69
    ]{}
    1.64
    "`
    1.59
     between
    1.58
     weakly
    1.54
    borne
    1.48
     uniformly
    1.47
    Activations Density 0.127%

    No Known Activations