© 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. 30572
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate legal actions or 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
    181
    +0.16
    0.9%
    454
    +0.13
    0.7%
    388
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.16
    0.14
    140
    +0.13
    0.14
    209
    +0.12
    0.13
    Negative Logits
     stride
    -1.50
    "?
    -1.49
    istas
    -1.48
    selves
    -1.48
    ilent
    -1.46
    own
    -1.43
    furt
    -1.38
    agers
    -1.37
    idelines
    -1.36
     door
    -1.36
    POSITIVE LOGITS
    jection
    1.49
    fert
    1.46
     Breast
    1.35
     pled
    1.32
     Pruss
    1.31
    ject
    1.30
    ctomy
    1.27
     replacement
    1.26
    lle
    1.23
     MCF
    1.22
    Activations Density 0.283%

    No Known Activations