© 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. 26524
    Prev
    Next
    INDEX
    Explanations

    the presence of selection commands or prompts

    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
    376
    +0.15
    0.8%
    59
    +0.12
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.15
    0.01
    0
    +0.12
    0.01
    435
    +0.12
    0.01
    Negative Logits
    ĥ½
    -1.52
    ĵ
    -1.51
    ters
    -1.47
    ³
    -1.37
     its
    -1.34
     her
    -1.32
    '?"
    -1.32
     glob
    -1.30
     degener
    -1.29
    ctors
    -1.28
    POSITIVE LOGITS
    iva
    1.84
    istar
    1.84
     era
    1.71
    ivo
    1.70
    oon
    1.68
    arez
    1.65
    aeda
    1.57
    vez
    1.54
    imen
    1.53
    ilage
    1.52
    Activations Density 0.005%

    No Known Activations