© 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. 26750
    Prev
    Next
    INDEX
    Explanations

    expressions indicating enhancement or improvement

    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
    156
    +0.23
    1.3%
    376
    +0.15
    0.9%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.23
    0.02
    370
    +0.15
    0.01
    422
    +0.12
    0.01
    Negative Logits
    Ĵ
    -1.99
    ĥ½
    -1.82
    ¿½
    -1.81
    ĨĴ
    -1.67
    ello
    -1.64
    ksen
    -1.63
    Ī
    -1.57
    ®
    -1.55
    İ
    -1.55
    ©
    -1.51
    POSITIVE LOGITS
     transparency
    1.50
     integration
    1.40
    uate
    1.40
     measures
    1.36
     BSD
    1.35
    pread
    1.34
     meas
    1.26
    iating
    1.25
     ones
    1.25
     detection
    1.25
    Activations Density 0.012%

    No Known Activations