© 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. 29423
    Prev
    Next
    INDEX
    Explanations

    references to specific legal case citations and their 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
    245
    +0.13
    0.7%
    307
    +0.12
    0.7%
    290
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.13
    0.04
    245
    +0.12
    0.04
    445
    +0.12
    0.03
    Negative Logits
    cha
    -1.74
     ever
    -1.66
     neither
    -1.56
    cht
    -1.50
    usterity
    -1.48
     about
    -1.47
     convicted
    -1.47
    ching
    -1.45
     afraid
    -1.44
     ?>
    -1.44
    POSITIVE LOGITS
    MSO
    1.68
    sky
    1.67
    rd
    1.66
    °
    1.62
    nd
    1.62
    ska
    1.57
    ®
    1.56
    sk
    1.53
    isma
    1.51
    ise
    1.51
    Activations Density 0.043%

    No Known Activations