© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    67
    +0.16
    0.9%
    252
    +0.15
    0.9%
    461
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.16
    0.05
    437
    +0.15
    0.03
    381
    +0.13
    0.03
    Negative Logits
     jurisdiction
    -1.56
     receivers
    -1.56
     prosecution
    -1.50
     judgment
    -1.44
     custody
    -1.41
     taxable
    -1.41
     recipe
    -1.40
    agles
    -1.36
    ller
    -1.34
    ameters
    -1.34
    POSITIVE LOGITS
    ł
    2.27
    Ģ
    2.09
    2.08
    ↵
    2.08
    ↵
    2.08
    ↵
    2.08
    ↵
    2.08
    2.08
    ↵
    2.08
    2.08
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.