© 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. 29449
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly those over 95, which may denote significant measurements or thresholds

    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
    369
    +0.20
    1.1%
    498
    +0.14
    0.8%
    22
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.20
    0.03
    151
    +0.14
    0.03
    109
    +0.13
    0.02
    Negative Logits
    inate
    -1.61
    unnel
    -1.59
    iorari
    -1.58
    eness
    -1.57
    estine
    -1.57
    sworth
    -1.55
    onia
    -1.52
    raft
    -1.48
     dissent
    -1.42
     probation
    -1.41
    POSITIVE LOGITS
    ĭ
    2.23
    ħ
    2.10
    ®
    2.03
    µ
    1.95
    ģ
    1.95
    Ľ
    1.83
    ¶
    1.81
    ª
    1.79
    ķ
    1.75
    »
    1.74
    Activations Density 1.949%

    No Known Activations