© 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. 2-MLP-SM
    11. 24837
    Prev
    Next
    INDEX
    Explanations

    words related to cancellation and diminished states

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    46
    +0.12
    0.7%
    344
    +0.12
    0.7%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.06
    46
    +0.12
    0.06
    198
    +0.11
    0.10
    Negative Logits
     etc
    -1.68
    selves
    -1.57
    idays
    -1.54
     “
    -1.52
     clicks
    -1.44
     margins
    -1.44
     attention
    -1.44
     odds
    -1.42
     audience
    -1.41
     shots
    -1.39
    POSITIVE LOGITS
     prevailed
    1.59
    enum
    1.48
     promul
    1.48
    ascii
    1.46
     âĻª"
    1.44
    uder
    1.43
     endemic
    1.42
    rika
    1.41
    uda
    1.40
    attr
    1.40
    Activations Density 2.428%

    No Known Activations