© 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. 28799
    Prev
    Next
    INDEX
    Explanations

    references to specific legal codes or statutes

    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
    247
    +0.13
    0.7%
    97
    +0.13
    0.7%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.13
    0.05
    307
    +0.13
    0.05
    412
    +0.12
    0.04
    Negative Logits
    www
    -1.40
     redistribute
    -1.39
    cht
    -1.37
    vall
    -1.33
    ributors
    -1.29
     refer
    -1.29
    wasysym
    -1.29
     who
    -1.27
    icious
    -1.27
    si
    -1.26
    POSITIVE LOGITS
    til
    1.54
    istic
    1.53
    ounces
    1.51
    shire
    1.50
     Caption
    1.44
    furt
    1.43
    ün
    1.41
    onas
    1.39
    stood
    1.38
    fly
    1.35
    Activations Density 0.083%

    No Known Activations