© 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. 29175
    Prev
    Next
    INDEX
    Explanations

    references to legal or licensing terms

    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
    417
    +0.12
    0.7%
    274
    +0.12
    0.7%
    267
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.12
    0.04
    267
    +0.12
    0.03
    207
    +0.12
    0.03
    Negative Logits
    omitempty
    -1.49
    ferences
    -1.46
    said
    -1.45
    ills
    -1.42
     immediate
    -1.41
     said
    -1.40
    here
    -1.40
    aphyl
    -1.39
    cha
    -1.37
     entire
    -1.35
    POSITIVE LOGITS
    º
    1.94
    ignon
    1.88
    ieu
    1.80
    PHA
    1.79
    inux
    1.74
    ®
    1.70
    IOR
    1.67
    arman
    1.66
    egal
    1.66
    ĸ
    1.66
    Activations Density 0.237%

    No Known Activations