© 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 EvalsExportsAPI 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. 28705
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal compliance and applicability

    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
    376
    +0.15
    0.8%
    40
    +0.10
    0.6%
    178
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.15
    0.02
    178
    +0.10
    0.02
    199
    +0.10
    0.02
    Negative Logits
    orian
    -2.24
    -)
    -1.73
    Ļª
    -1.68
    ori
    -1.55
    anos
    -1.53
    enth
    -1.51
    oppy
    -1.48
    ager
    -1.40
    arth
    -1.37
    Į
    -1.36
    POSITIVE LOGITS
    iances
    1.62
     laws
    1.47
     ones
    1.46
    coding
    1.44
    ISPR
    1.43
    iator
    1.42
    rences
    1.41
     governing
    1.39
     therein
    1.38
     governor
    1.36
    Activations Density 0.929%

    No Known Activations