© 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. 28912
    Prev
    Next
    INDEX
    Explanations

    instances of accidental or unintended actions

    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
    +0.24
    1.4%
    156
    +0.23
    1.4%
    148
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.24
    0.01
    171
    +0.23
    0.01
    148
    +0.18
    0.01
    Negative Logits
    ħ
    -2.05
    »¿
    -2.01
    Ī
    -1.87
    Ĵ
    -1.81
    Ķ
    -1.75
    IJ
    -1.74
    Ĺ
    -1.74
    ↵↵
    -1.68
     ↵
    -1.68
    č↵
    -1.68
    POSITIVE LOGITS
     necrosis
    1.59
     insult
    1.44
     reflections
    1.42
     wounded
    1.42
     collisions
    1.39
     enlarge
    1.38
     deletions
    1.38
     deceased
    1.35
    oplan
    1.35
    death
    1.35
    Activations Density 0.020%

    No Known Activations